Datasets:

librarian-bots
/

model_cards_with_metadata

Dataset card Data Studio Files Files and versions Community

Split (1)

train · 691k rows

Search is not available for this dataset

modelId stringlengths 5 137	author stringlengths 2 42	last_modified unknowndate 2020-02-15 11:33:14 2025-03-29 00:36:43	downloads int64 0 223M	likes int64 0 11.7k	library_name stringclasses 401 values	tags sequencelengths 1 4.05k	pipeline_tag stringclasses 54 values	createdAt unknowndate 2022-03-02 23:29:04 2025-03-29 00:36:28	card stringlengths 11 1.01M
adityarra07/whisper-med-LoRA_noise_128_128_3k	adityarra07	"2024-04-02T19:12:33Z"	0	0	null	[ "generated_from_trainer", "base_model:openai/whisper-medium", "base_model:finetune:openai/whisper-medium", "license:apache-2.0", "region:us" ]	null	"2024-04-02T17:31:57Z"	--- license: apache-2.0 base_model: openai/whisper-medium tags: - generated_from_trainer metrics: - wer model-index: - name: whisper-medium-LoRA_nosie_aug_128 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # whisper-medium-LoRA_nosie_aug_128 This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.6571 - Wer: 23.9693 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Wer \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:-------:\| \| 3.0441 \| 1.0 \| 188 \| 2.0325 \| 37.2963 \| \| 1.1676 \| 2.0 \| 376 \| 0.7900 \| 39.0221 \| \| 0.6457 \| 3.0 \| 564 \| 0.7016 \| 34.6117 \| \| 0.5808 \| 4.0 \| 752 \| 0.6675 \| 23.8734 \| \| 0.552 \| 5.0 \| 940 \| 0.6571 \| 23.9693 \| ### Framework versions - Transformers 4.33.1 - Pytorch 2.0.1+cu117 - Datasets 2.14.5 - Tokenizers 0.13.3
Asheyy/dogbooth	Asheyy	"2023-09-20T10:01:40Z"	0	0	diffusers	[ "diffusers", "tensorboard", "safetensors", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "dreambooth", "base_model:stabilityai/stable-diffusion-2-1", "base_model:finetune:stabilityai/stable-diffusion-2-1", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	"2023-09-17T09:20:41Z"	--- license: creativeml-openrail-m base_model: stabilityai/stable-diffusion-2-1 instance_prompt: a photo of [v]dog tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - dreambooth inference: true --- # DreamBooth - Asheyy/dogbooth This is a dreambooth model derived from stabilityai/stable-diffusion-2-1. The weights were trained on a photo of [v]dog using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following. DreamBooth for the text encoder was enabled: False.
cutelemonlili/llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview	cutelemonlili	"2024-12-29T13:54:30Z"	138	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "llama-factory", "full", "generated_from_trainer", "conversational", "base_model:TaiGary/llama3.2_3b_NuminaMath-CoT_100k", "base_model:finetune:TaiGary/llama3.2_3b_NuminaMath-CoT_100k", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2024-12-29T13:52:57Z"	--- library_name: transformers license: other base_model: TaiGary/llama3.2_3b_NuminaMath-CoT_100k tags: - llama-factory - full - generated_from_trainer model-index: - name: MATH_training_Qwen_QwQ_32B_Preview results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # MATH_training_Qwen_QwQ_32B_Preview This model is a fine-tuned version of [TaiGary/llama3.2_3b_NuminaMath-CoT_100k](https://huggingface.co/TaiGary/llama3.2_3b_NuminaMath-CoT_100k) on the MATH_training_Qwen_QwQ_32B_Preview dataset. It achieves the following results on the evaluation set: - Loss: 0.4254 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 2 - eval_batch_size: 1 - seed: 42 - distributed_type: multi-GPU - num_devices: 4 - total_train_batch_size: 8 - total_eval_batch_size: 4 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - num_epochs: 2 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 0.4352 \| 0.2999 \| 200 \| 0.4800 \| \| 0.4569 \| 0.5997 \| 400 \| 0.4496 \| \| 0.4985 \| 0.8996 \| 600 \| 0.4304 \| \| 0.3238 \| 1.1994 \| 800 \| 0.4392 \| \| 0.2457 \| 1.4993 \| 1000 \| 0.4288 \| \| 0.2077 \| 1.7991 \| 1200 \| 0.4263 \| ### Framework versions - Transformers 4.46.1 - Pytorch 2.5.1+cu124 - Datasets 3.1.0 - Tokenizers 0.20.3
yodayo-ai/nephra_v1.0	yodayo-ai	"2024-06-19T18:13:02Z"	192	20	transformers	[ "transformers", "pytorch", "llama", "text-generation", "conversational", "en", "base_model:meta-llama/Meta-Llama-3-8B", "base_model:finetune:meta-llama/Meta-Llama-3-8B", "license:llama3", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2024-06-17T21:26:57Z"	--- license: llama3 language: - en base_model: meta-llama/Meta-Llama-3-8B --- ## Overview nephra v1 is primarily a model built for roleplaying sessions, trained on roleplay and instruction-style datasets. ## Model Details - Developed by: [Sao10K](https://huggingface.co/Sao10K) - Model type: Text-based Large Language Model - License: [Meta Llama 3 Community License Agreement](https://huggingface.co/meta-llama/Meta-Llama-3-8B/blob/main/LICENSE) - Finetuned from model: [Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) ## Inference Guidelines ```python import transformers import torch model_id = "yodayo-ai/nephra_v1.0" pipeline = transformers.pipeline( "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device_map="auto", ) messages = [ {"role": "system", "content": "You are to play the role of a cheerful assistant."}, {"role": "user", "content": "Hi there, how's your day?"}, ] prompt = pipeline.tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) outputs = pipeline( prompt, max_new_tokens=512, eos_token_id=[ pipeline.tokenizer.convert_tokens_to_ids("<\|eot_id\|>"), pipeline.tokenizer.eos_token_id, ], do_sample=True, temperature=1.12, min_p=0.075, ) print(outputs[0]["generated_text"][len(prompt):]) ``` ### Recommended Settings To guide the model to generate high-quality responses, here are the ideal settings: ``` Prompt Format: Same Prompt Format as Llama-3-Instruct Temperature - 1.12 min-p: 0.075 Repetition Penalty: 1.1 Custom Stopping Strings: "\n{{user}}", "<" , "```" , -> Has occasional broken generations. ``` ## License Nephra v1 falls under [META LLAMA 3 COMMUNITY LICENSE AGREEMENT](https://huggingface.co/meta-llama/Meta-Llama-3-8B/blob/main/LICENSE).
JoshELambert/markets	JoshELambert	"2023-07-07T15:53:15Z"	6	0	sentence-transformers	[ "sentence-transformers", "pytorch", "mpnet", "setfit", "text-classification", "arxiv:2209.11055", "license:apache-2.0", "region:us" ]	text-classification	"2023-07-07T15:12:22Z"	--- license: apache-2.0 tags: - setfit - sentence-transformers - text-classification pipeline_tag: text-classification --- # /var/folders/8x/qp375g154zg3h3ktpt_8tyqw0000gn/T/tmp44tdhqys/JoshELambert/markets This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves: 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning. 2. Training a classification head with features from the fine-tuned Sentence Transformer. ## Usage To use this model for inference, first install the SetFit library: ```bash python -m pip install setfit ``` You can then run inference as follows: ```python from setfit import SetFitModel # Download from Hub and run inference model = SetFitModel.from_pretrained("/var/folders/8x/qp375g154zg3h3ktpt_8tyqw0000gn/T/tmp44tdhqys/JoshELambert/markets") # Run inference preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"]) ``` ## BibTeX entry and citation info ```bibtex @article{https://doi.org/10.48550/arxiv.2209.11055, doi = {10.48550/ARXIV.2209.11055}, url = {https://arxiv.org/abs/2209.11055}, author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren}, keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences}, title = {Efficient Few-Shot Learning Without Prompts}, publisher = {arXiv}, year = {2022}, copyright = {Creative Commons Attribution 4.0 International} } ```
menutp/profanity-fr-65ac	menutp	"2024-01-25T22:52:09Z"	92	0	transformers	[ "transformers", "safetensors", "roberta", "text-classification", "license:wtfpl", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	"2024-01-25T22:19:22Z"	--- license: wtfpl --- this model was trained on 95% of my dataset menutp/hate_speech-fr_mini and validated on the last 5% it reached 65% accuracy. labels are to be interpreted as follow : ``` { 0: "neutral", 1: "toxic", 2: "severe toxic", 3: "obscene", 4: "threat", 5: "insult", 6: "identity hate", 7: "generally_offensive" } ``` due to the lack of training data for the label between 1 and 6 only label 0 and 7 are to be trusted
mradermacher/MopeyMule-Blackroot-8B-i1-GGUF	mradermacher	"2024-12-16T02:37:23Z"	39	0	transformers	[ "transformers", "gguf", "mergekit", "merge", "en", "base_model:Cas-Warehouse/Llama-3-MopeyMule-Blackroot-8B", "base_model:quantized:Cas-Warehouse/Llama-3-MopeyMule-Blackroot-8B", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	null	"2024-06-14T05:25:28Z"	--- base_model: Cas-Warehouse/Llama-3-MopeyMule-Blackroot-8B language: - en library_name: transformers quantized_by: mradermacher tags: - mergekit - merge --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/Cas-Warehouse/Llama-3-MopeyMule-Blackroot-8B <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/MopeyMule-Blackroot-8B-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/MopeyMule-Blackroot-8B-i1-GGUF/resolve/main/MopeyMule-Blackroot-8B.i1-IQ1_S.gguf) \| i1-IQ1_S \| 2.1 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/MopeyMule-Blackroot-8B-i1-GGUF/resolve/main/MopeyMule-Blackroot-8B.i1-IQ1_M.gguf) \| i1-IQ1_M \| 2.3 \| mostly desperate \| \| [GGUF](https://huggingface.co/mradermacher/MopeyMule-Blackroot-8B-i1-GGUF/resolve/main/MopeyMule-Blackroot-8B.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 2.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/MopeyMule-Blackroot-8B-i1-GGUF/resolve/main/MopeyMule-Blackroot-8B.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 2.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/MopeyMule-Blackroot-8B-i1-GGUF/resolve/main/MopeyMule-Blackroot-8B.i1-IQ2_S.gguf) \| i1-IQ2_S \| 2.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/MopeyMule-Blackroot-8B-i1-GGUF/resolve/main/MopeyMule-Blackroot-8B.i1-IQ2_M.gguf) \| i1-IQ2_M \| 3.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/MopeyMule-Blackroot-8B-i1-GGUF/resolve/main/MopeyMule-Blackroot-8B.i1-Q2_K.gguf) \| i1-Q2_K \| 3.3 \| IQ3_XXS probably better \| \| [GGUF](https://huggingface.co/mradermacher/MopeyMule-Blackroot-8B-i1-GGUF/resolve/main/MopeyMule-Blackroot-8B.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 3.4 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/MopeyMule-Blackroot-8B-i1-GGUF/resolve/main/MopeyMule-Blackroot-8B.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 3.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/MopeyMule-Blackroot-8B-i1-GGUF/resolve/main/MopeyMule-Blackroot-8B.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 3.8 \| IQ3_XS probably better \| \| [GGUF](https://huggingface.co/mradermacher/MopeyMule-Blackroot-8B-i1-GGUF/resolve/main/MopeyMule-Blackroot-8B.i1-IQ3_S.gguf) \| i1-IQ3_S \| 3.8 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/MopeyMule-Blackroot-8B-i1-GGUF/resolve/main/MopeyMule-Blackroot-8B.i1-IQ3_M.gguf) \| i1-IQ3_M \| 3.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/MopeyMule-Blackroot-8B-i1-GGUF/resolve/main/MopeyMule-Blackroot-8B.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 4.1 \| IQ3_S probably better \| \| [GGUF](https://huggingface.co/mradermacher/MopeyMule-Blackroot-8B-i1-GGUF/resolve/main/MopeyMule-Blackroot-8B.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 4.4 \| IQ3_M probably better \| \| [GGUF](https://huggingface.co/mradermacher/MopeyMule-Blackroot-8B-i1-GGUF/resolve/main/MopeyMule-Blackroot-8B.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 4.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/MopeyMule-Blackroot-8B-i1-GGUF/resolve/main/MopeyMule-Blackroot-8B.i1-Q4_0.gguf) \| i1-Q4_0 \| 4.8 \| fast, low quality \| \| [GGUF](https://huggingface.co/mradermacher/MopeyMule-Blackroot-8B-i1-GGUF/resolve/main/MopeyMule-Blackroot-8B.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 4.8 \| optimal size/speed/quality \| \| [GGUF](https://huggingface.co/mradermacher/MopeyMule-Blackroot-8B-i1-GGUF/resolve/main/MopeyMule-Blackroot-8B.i1-Q4_K_M.gguf) \| i1-Q4_K_M \| 5.0 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/MopeyMule-Blackroot-8B-i1-GGUF/resolve/main/MopeyMule-Blackroot-8B.i1-Q5_K_S.gguf) \| i1-Q5_K_S \| 5.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/MopeyMule-Blackroot-8B-i1-GGUF/resolve/main/MopeyMule-Blackroot-8B.i1-Q5_K_M.gguf) \| i1-Q5_K_M \| 5.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/MopeyMule-Blackroot-8B-i1-GGUF/resolve/main/MopeyMule-Blackroot-8B.i1-Q6_K.gguf) \| i1-Q6_K \| 6.7 \| practically like static Q6_K \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. <!-- end -->
lesso/376486a9-a13d-4285-837d-92a603f6e5de	lesso	"2025-02-09T00:13:12Z"	8	0	peft	[ "peft", "safetensors", "mixtral", "axolotl", "generated_from_trainer", "base_model:TitanML/tiny-mixtral", "base_model:adapter:TitanML/tiny-mixtral", "region:us" ]	null	"2025-02-07T09:20:25Z"	--- library_name: peft base_model: TitanML/tiny-mixtral tags: - axolotl - generated_from_trainer model-index: - name: 376486a9-a13d-4285-837d-92a603f6e5de results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <br> # 376486a9-a13d-4285-837d-92a603f6e5de This model is a fine-tuned version of [TitanML/tiny-mixtral](https://huggingface.co/TitanML/tiny-mixtral) on the None dataset. It achieves the following results on the evaluation set: - Loss: 8.5250 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001006 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 8 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 10 - training_steps: 200 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 10.5357 \| 0.0012 \| 1 \| 10.5768 \| \| 9.0359 \| 0.0593 \| 50 \| 8.9945 \| \| 9.412 \| 0.1186 \| 100 \| 8.7903 \| \| 9.381 \| 0.1778 \| 150 \| 8.6029 \| \| 8.9243 \| 0.2371 \| 200 \| 8.5250 \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
lrios/sdxl-lora-solana-logo	lrios	"2025-02-21T20:14:44Z"	0	0	diffusers	[ "diffusers", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "text-to-image", "diffusers-training", "lora", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0", "license:creativeml-openrail-m", "region:us" ]	text-to-image	"2025-02-21T18:42:42Z"	--- base_model: stabilityai/stable-diffusion-xl-base-1.0 library_name: diffusers license: creativeml-openrail-m inference: true tags: - stable-diffusion-xl - stable-diffusion-xl-diffusers - text-to-image - diffusers - diffusers-training - lora - stable-diffusion-xl - stable-diffusion-xl-diffusers - text-to-image - diffusers - diffusers-training - lora --- <!-- This model card has been generated automatically according to the information the training script had access to. You should probably proofread and complete it, then remove this comment. --> # LoRA text2image fine-tuning - lrios/sdxl-lora-solana-logo These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were fine-tuned on the None dataset. You can find some example images in the following. ![img_0](./image_0.png) ![img_1](./image_1.png) ![img_2](./image_2.png) ![img_3](./image_3.png) LoRA for the text encoder was enabled: False. Special VAE used for training: madebyollin/sdxl-vae-fp16-fix. ## Intended uses & limitations #### How to use ```python # TODO: add an example code snippet for running this diffusion pipeline ``` #### Limitations and bias [TODO: provide examples of latent issues and potential remediations] ## Training details [TODO: describe the data used to train the model]
vedalken/ML6-interview	vedalken	"2025-02-18T08:00:49Z"	1	0	transformers	[ "transformers", "safetensors", "roberta", "text-classification", "en", "base_model:FacebookAI/roberta-base", "base_model:finetune:FacebookAI/roberta-base", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	"2025-02-17T16:54:10Z"	--- license: apache-2.0 language: - en metrics: - accuracy base_model: - FacebookAI/roberta-base pipeline_tag: text-classification library_name: transformers --- Roberta-base trained on the dataset for job description classification. Repo of the interview: https://bitbucket.org/ml6team/challenge-classify-job-descriptions.git/src For the training code just send me a message or comment in this repo.
buddhilive/roberta-finetuned-squad	buddhilive	"2023-09-09T19:44:51Z"	59	0	transformers	[ "transformers", "tf", "roberta", "question-answering", "generated_from_keras_callback", "base_model:FacebookAI/roberta-base", "base_model:finetune:FacebookAI/roberta-base", "license:mit", "endpoints_compatible", "region:us" ]	question-answering	"2023-09-09T19:05:33Z"	--- license: mit base_model: roberta-base tags: - generated_from_keras_callback model-index: - name: buddhilive/roberta-finetuned-squad results: [] --- <!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. --> # buddhilive/roberta-finetuned-squad This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.6953 - Validation Loss: 0.0 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1000, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results \| Train Loss \| Validation Loss \| Epoch \| \|:----------:\|:---------------:\|:-----:\| \| 1.2629 \| 0.0 \| 0 \| \| 0.7907 \| 0.0 \| 1 \| \| 0.6953 \| 0.0 \| 2 \| ### Framework versions - Transformers 4.33.1 - TensorFlow 2.13.0 - Datasets 2.14.5 - Tokenizers 0.13.3
nmcco/18-qwen-1gpu	nmcco	"2025-03-18T21:10:12Z"	0	0	transformers	[ "transformers", "safetensors", "generated_from_trainer", "trl", "sft", "base_model:nmcco/qwen-2.5-3b-speakertokens", "base_model:finetune:nmcco/qwen-2.5-3b-speakertokens", "endpoints_compatible", "region:us" ]	null	"2025-03-18T20:10:25Z"	--- base_model: nmcco/qwen-2.5-3b-speakertokens library_name: transformers model_name: 18-qwen-1gpu tags: - generated_from_trainer - trl - sft licence: license --- # Model Card for 18-qwen-1gpu This model is a fine-tuned version of [nmcco/qwen-2.5-3b-speakertokens](https://huggingface.co/nmcco/qwen-2.5-3b-speakertokens). It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="nmcco/18-qwen-1gpu", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/hwerzog-huh/huggingface/runs/wyfma7e8) This model was trained with SFT. ### Framework versions - TRL: 0.14.0 - Transformers: 4.48.2 - Pytorch: 2.4.1 - Datasets: 3.2.0 - Tokenizers: 0.21.0 ## Citations Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
tronsdds/Qwen-Qwen1.5-0.5B-1724517284	tronsdds	"2024-08-24T16:35:23Z"	5	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:Qwen/Qwen1.5-0.5B", "base_model:adapter:Qwen/Qwen1.5-0.5B", "region:us" ]	null	"2024-08-24T16:34:44Z"	--- base_model: Qwen/Qwen1.5-0.5B library_name: peft --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.12.0
mradermacher/MiquTotalMix-70B-i1-GGUF	mradermacher	"2024-05-06T06:03:19Z"	17	0	transformers	[ "transformers", "gguf", "mergekit", "merge", "en", "base_model:Undi95/MiquTotalMix-70B", "base_model:quantized:Undi95/MiquTotalMix-70B", "endpoints_compatible", "region:us", "conversational" ]	null	"2024-03-22T22:36:45Z"	--- base_model: Undi95/MiquTotalMix-70B language: - en library_name: transformers quantized_by: mradermacher tags: - mergekit - merge --- ## About weighted/imatrix quants of https://huggingface.co/Undi95/MiquTotalMix-70B <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/MiquTotalMix-70B-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-IQ1_S.gguf) \| i1-IQ1_S \| 15.0 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 18.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 20.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-IQ2_S.gguf) \| i1-IQ2_S \| 21.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-IQ2_M.gguf) \| i1-IQ2_M \| 23.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q2_K.gguf) \| i1-Q2_K \| 25.9 \| IQ3_XXS probably better \| \| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 27.0 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 28.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-IQ3_S.gguf) \| i1-IQ3_S \| 30.3 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 30.3 \| IQ3_XS probably better \| \| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-IQ3_M.gguf) \| i1-IQ3_M \| 31.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 33.7 \| IQ3_S probably better \| \| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 36.6 \| IQ3_M probably better \| \| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 37.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-IQ4_NL.gguf) \| i1-IQ4_NL \| 39.4 \| prefer IQ4_XS \| \| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 39.7 \| optimal size/speed/quality \| \| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q4_K_M.gguf) \| i1-Q4_K_M \| 41.8 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q5_K_S.gguf) \| i1-Q5_K_S \| 47.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q5_K_M.gguf) \| i1-Q5_K_M \| 49.2 \| \| \| [PART 1](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q6_K.gguf.part2of2) \| i1-Q6_K \| 57.0 \| practically like static Q6_K \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
daveempire/joker_teller	daveempire	"2025-03-26T15:45:11Z"	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	"2025-03-26T15:45:11Z"	--- license: creativeml-openrail-m ---
SmallDoge/qwen7b_instruct_shortcot_smallthoughts25k	SmallDoge	"2025-03-17T06:14:51Z"	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2025-03-17T05:52:52Z"	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
havinash-ai/377d8250-51d3-4829-b83f-26d1ea9dfb50	havinash-ai	"2025-01-17T00:23:34Z"	6	0	peft	[ "peft", "safetensors", "phi3", "axolotl", "generated_from_trainer", "custom_code", "base_model:microsoft/Phi-3-mini-128k-instruct", "base_model:adapter:microsoft/Phi-3-mini-128k-instruct", "license:mit", "region:us" ]	null	"2025-01-17T00:21:56Z"	--- library_name: peft license: mit base_model: microsoft/Phi-3-mini-128k-instruct tags: - axolotl - generated_from_trainer model-index: - name: 377d8250-51d3-4829-b83f-26d1ea9dfb50 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.4.1` ```yaml adapter: lora base_model: microsoft/Phi-3-mini-128k-instruct bf16: auto chat_template: llama3 dataset_prepared_path: null datasets: - data_files: - 328d72eb04626276_train_data.json ds_type: json format: custom path: /workspace/input_data/328d72eb04626276_train_data.json type: field_input: history_data field_instruction: current_conv_data field_output: response_supporter format: '{instruction} {input}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 128 eval_table_size: null evals_per_epoch: 4 flash_attention: false fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 4 gradient_checkpointing: false group_by_length: false hub_model_id: havinash-ai/377d8250-51d3-4829-b83f-26d1ea9dfb50 hub_repo: null hub_strategy: checkpoint hub_token: null learning_rate: 0.0002 load_in_4bit: false load_in_8bit: false local_rank: null logging_steps: 1 lora_alpha: 16 lora_dropout: 0.05 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 8 lora_target_linear: true lr_scheduler: cosine max_steps: 10 micro_batch_size: 2 mlflow_experiment_name: /tmp/328d72eb04626276_train_data.json model_type: AutoModelForCausalLM num_epochs: 1 optimizer: adamw_bnb_8bit output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false saves_per_epoch: 4 sequence_len: 512 strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: 8b7ad9ea-6630-4a3b-83b5-7c7c26a52fac wandb_project: Mine-SN56-2-Gradients-On-Demand wandb_run: your_name wandb_runid: 8b7ad9ea-6630-4a3b-83b5-7c7c26a52fac warmup_steps: 10 weight_decay: 0.0 xformers_attention: null ``` </details><br> # 377d8250-51d3-4829-b83f-26d1ea9dfb50 This model is a fine-tuned version of [microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.7519 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 10 - training_steps: 10 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 3.9583 \| 0.0008 \| 1 \| 0.9906 \| \| 3.8546 \| 0.0023 \| 3 \| 0.9854 \| \| 3.3839 \| 0.0046 \| 6 \| 0.9354 \| \| 3.3853 \| 0.0069 \| 9 \| 0.7519 \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
laquythang/8b0b95a8-cd27-4243-8419-09768a319970	laquythang	"2025-01-13T21:30:36Z"	12	0	peft	[ "peft", "safetensors", "llama", "axolotl", "generated_from_trainer", "base_model:unsloth/SmolLM2-1.7B", "base_model:adapter:unsloth/SmolLM2-1.7B", "license:apache-2.0", "8-bit", "bitsandbytes", "region:us" ]	null	"2025-01-13T21:21:28Z"	--- library_name: peft license: apache-2.0 base_model: unsloth/SmolLM2-1.7B tags: - axolotl - generated_from_trainer model-index: - name: 8b0b95a8-cd27-4243-8419-09768a319970 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.4.1` ```yaml adapter: lora base_model: unsloth/SmolLM2-1.7B bf16: auto chat_template: llama3 dataset_prepared_path: null datasets: - data_files: - f58909f3ef8c0453_train_data.json ds_type: json format: custom path: /workspace/input_data/f58909f3ef8c0453_train_data.json type: field_input: caption field_instruction: question field_output: answer format: '{instruction} {input}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 128 eval_table_size: null evals_per_epoch: 1 flash_attention: true fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 4 gradient_checkpointing: true gradient_clipping: 1.0 group_by_length: false hub_model_id: laquythang/8b0b95a8-cd27-4243-8419-09768a319970 hub_repo: null hub_strategy: end hub_token: null learning_rate: 5.0e-05 load_in_4bit: true load_in_8bit: true local_rank: null logging_steps: 1 lora_alpha: 16 lora_dropout: 0.05 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 8 lora_target_linear: true lr_scheduler: cosine max_steps: 200 micro_batch_size: 2 mlflow_experiment_name: /tmp/f58909f3ef8c0453_train_data.json model_type: AutoModelForCausalLM num_epochs: 1 optimizer: adamw_bnb_8bit output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false saves_per_epoch: 1 sequence_len: 1024 strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: 773751f8-2eac-44c5-b605-ae427895e535 wandb_project: Gradients-On-Demand wandb_run: your_name wandb_runid: 773751f8-2eac-44c5-b605-ae427895e535 warmup_steps: 5 weight_decay: 0.01 xformers_attention: true ``` </details><br> # 8b0b95a8-cd27-4243-8419-09768a319970 This model is a fine-tuned version of [unsloth/SmolLM2-1.7B](https://huggingface.co/unsloth/SmolLM2-1.7B) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.4695 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 5 - training_steps: 200 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 0.506 \| 0.2905 \| 200 \| 0.4695 \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
tousek/llama_3_Mike-unsloth.Q4-K-M.gguf	tousek	"2024-06-17T14:49:18Z"	0	0	transformers	[ "transformers", "safetensors", "text-generation-inference", "unsloth", "llama", "trl", "en", "base_model:unsloth/llama-3-8b-bnb-4bit", "base_model:finetune:unsloth/llama-3-8b-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	"2024-06-17T14:48:52Z"	--- language: - en license: apache-2.0 tags: - text-generation-inference - transformers - unsloth - llama - trl base_model: unsloth/llama-3-8b-bnb-4bit --- # Uploaded model - Developed by: tousek - License: apache-2.0 - Finetuned from model : unsloth/llama-3-8b-bnb-4bit This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
pt-sk/VAE	pt-sk	"2024-05-27T14:17:31Z"	0	0	null	[ "license:mit", "region:us" ]	null	"2024-05-26T09:01:13Z"	--- license: mit --- 1. Encoder_Decoder_1_EPOCH and Encoder_Decoder_2_EPOCH trained on celebA HQ resized 256 x 256 dataset for 2 epochs(30000 samples) 2. used 2nd epoch check point to further train on face hq dataset resized 256 x 256 dataset for 1 epochs(70000 samples)
mamun4105/q-Taxi-v3	mamun4105	"2023-06-13T05:25:55Z"	0	0	null	[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	reinforcement-learning	"2023-06-12T18:57:07Z"	--- tags: - Taxi-v3 - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-Taxi-v3 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Taxi-v3 type: Taxi-v3 metrics: - type: mean_reward value: 7.56 +/- 2.71 name: mean_reward verified: false --- # Q-Learning Agent playing1 FrozenLake-v1 This is a trained model of a Q-Learning agent playing FrozenLake-v1 . ## Usage ```python model = load_from_hub(repo_id="mamun4105/q-Taxi-v3", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```
smp-hub/resnext101_32x32d.instagram	smp-hub	"2025-01-15T17:52:46Z"	10	0	segmentation-models-pytorch	[ "segmentation-models-pytorch", "safetensors", "image-classification", "pytorch", "resnext", "license:other", "region:us" ]	image-classification	"2025-01-14T22:47:00Z"	--- library_name: segmentation-models-pytorch license: other pipeline_tag: image-classification tags: - segmentation-models-pytorch - image-classification - pytorch - resnext languages: - python --- # Model card for resnext101_32x32d. This repository contains the `instagram` pre-trained weights for the `resnext101_32x32d` model used as encoder in the [segmentation-models-pytorch](https://github.com/qubvel-org/segmentation_models.pytorch) library. ### Example usage: 1. Install the library: ```bash pip install segmentation-models-pytorch ``` 2. Use the encoder in your code: ```python import segmentation_models_pytorch as smp model = smp.Unet("resnext101_32x32d", encoder_weights="instagram") ``` ### References - Github: https://github.com/qubvel/segmentation_models.pytorch - Docs: https://smp.readthedocs.io/en/latest/ - Original weights URL: https://download.pytorch.org/models/ig_resnext101_32x32-e4b90b00.pth
lesso03/234fdb1b-7ef8-41a4-8274-e4be1e14f795	lesso03	"2025-01-03T03:00:49Z"	5	0	peft	[ "peft", "safetensors", "llama", "axolotl", "generated_from_trainer", "custom_code", "base_model:NousResearch/Yarn-Llama-2-7b-128k", "base_model:adapter:NousResearch/Yarn-Llama-2-7b-128k", "region:us" ]	null	"2025-01-03T01:42:22Z"	--- library_name: peft base_model: NousResearch/Yarn-Llama-2-7b-128k tags: - axolotl - generated_from_trainer model-index: - name: 234fdb1b-7ef8-41a4-8274-e4be1e14f795 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.4.1` ```yaml adapter: lora base_model: NousResearch/Yarn-Llama-2-7b-128k bf16: true chat_template: llama3 datasets: - data_files: - b1e346db6e3ba891_train_data.json ds_type: json format: custom path: /workspace/input_data/b1e346db6e3ba891_train_data.json type: field_input: input field_instruction: task field_output: output format: '{instruction} {input}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 128 eval_table_size: null evals_per_epoch: 4 flash_attention: false fp16: false fsdp: null fsdp_config: null gradient_accumulation_steps: 2 gradient_checkpointing: true group_by_length: false hub_model_id: lesso03/234fdb1b-7ef8-41a4-8274-e4be1e14f795 hub_repo: null hub_strategy: checkpoint hub_token: null learning_rate: 1.0e-05 load_in_4bit: false load_in_8bit: false local_rank: null logging_steps: 1 lora_alpha: 32 lora_dropout: 0.05 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 16 lora_target_linear: true lr_scheduler: cosine max_memory: 0: 70GiB max_steps: 30 micro_batch_size: 4 mlflow_experiment_name: /tmp/b1e346db6e3ba891_train_data.json model_type: AutoModelForCausalLM num_epochs: 2 optimizer: adamw_torch output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false save_steps: 20 save_strategy: steps sequence_len: 1024 strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: 234fdb1b-7ef8-41a4-8274-e4be1e14f795 wandb_project: Gradients-On-Demand wandb_run: your_name wandb_runid: 234fdb1b-7ef8-41a4-8274-e4be1e14f795 warmup_steps: 5 weight_decay: 0.01 xformers_attention: false ``` </details><br> # 234fdb1b-7ef8-41a4-8274-e4be1e14f795 This model is a fine-tuned version of [NousResearch/Yarn-Llama-2-7b-128k](https://huggingface.co/NousResearch/Yarn-Llama-2-7b-128k) on the None dataset. It achieves the following results on the evaluation set: - Loss: 5.0115 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 8 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 5 - training_steps: 30 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 11.101 \| 0.0001 \| 1 \| 5.3590 \| \| 17.7617 \| 0.0003 \| 4 \| 5.3538 \| \| 7.2224 \| 0.0006 \| 8 \| 5.2922 \| \| 5.7201 \| 0.0009 \| 12 \| 5.2118 \| \| 7.3831 \| 0.0011 \| 16 \| 5.1252 \| \| 8.9314 \| 0.0014 \| 20 \| 5.0581 \| \| 9.4619 \| 0.0017 \| 24 \| 5.0237 \| \| 10.3213 \| 0.0020 \| 28 \| 5.0115 \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
N1ch0/chungli-ao-xlm-roberta-news	N1ch0	"2025-01-13T12:17:59Z"	165	0	transformers	[ "transformers", "safetensors", "xlm-roberta", "fill-mask", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	"2024-12-09T14:51:07Z"	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
akrishnan/gpt2-20M-unlearning-supersampled_biographies_x10_lr_0.0005_seed_123	akrishnan	"2025-02-24T17:16:57Z"	0	0	transformers	[ "transformers", "safetensors", "gpt2", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2025-02-24T17:12:39Z"	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
TitanML/Model-Cache	TitanML	"2024-04-24T10:02:00Z"	0	0	null	[ "region:us" ]	null	"2024-04-24T10:02:00Z"	# AWQ Cache Mapping HF model names to the names as saved in the TitanML directory.
lesso05/b83b4218-94d4-4b1b-b937-2b2afe93b724	lesso05	"2025-01-13T07:28:04Z"	10	0	peft	[ "peft", "safetensors", "mistral", "axolotl", "generated_from_trainer", "base_model:unsloth/Phi-3-mini-4k-instruct", "base_model:adapter:unsloth/Phi-3-mini-4k-instruct", "license:mit", "8-bit", "bitsandbytes", "region:us" ]	null	"2025-01-13T05:58:21Z"	--- library_name: peft license: mit base_model: unsloth/Phi-3-mini-4k-instruct tags: - axolotl - generated_from_trainer model-index: - name: b83b4218-94d4-4b1b-b937-2b2afe93b724 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.4.1` ```yaml adapter: lora base_model: unsloth/Phi-3-mini-4k-instruct bf16: true chat_template: llama3 datasets: - data_files: - dcb1f5719033089d_train_data.json ds_type: json format: custom path: /workspace/input_data/dcb1f5719033089d_train_data.json type: field_instruction: query field_output: response format: '{instruction}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: 2 eval_max_new_tokens: 128 eval_steps: 5 eval_table_size: null flash_attention: false fp16: false fsdp: null fsdp_config: null gradient_accumulation_steps: 4 gradient_checkpointing: false group_by_length: false hub_model_id: lesso05/b83b4218-94d4-4b1b-b937-2b2afe93b724 hub_repo: null hub_strategy: checkpoint hub_token: null learning_rate: 0.0002 load_in_4bit: false load_in_8bit: true local_rank: null logging_steps: 1 lora_alpha: 16 lora_dropout: 0.05 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 8 lora_target_linear: true lr_scheduler: cosine max_steps: 25 micro_batch_size: 2 mlflow_experiment_name: /tmp/dcb1f5719033089d_train_data.json model_type: AutoModelForCausalLM num_epochs: 1 optimizer: adamw_bnb_8bit output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false save_steps: 10 sequence_len: 512 strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: 1e37225f-b010-4451-a04e-631b19f1656c wandb_project: Gradients-On-Demand wandb_run: your_name wandb_runid: 1e37225f-b010-4451-a04e-631b19f1656c warmup_steps: 10 weight_decay: 0.0 xformers_attention: null ``` </details><br> # b83b4218-94d4-4b1b-b937-2b2afe93b724 This model is a fine-tuned version of [unsloth/Phi-3-mini-4k-instruct](https://huggingface.co/unsloth/Phi-3-mini-4k-instruct) on the None dataset. It achieves the following results on the evaluation set: - Loss: nan ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 10 - training_steps: 25 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 0.0 \| 0.0000 \| 1 \| nan \| \| 0.0 \| 0.0002 \| 5 \| nan \| \| 0.0 \| 0.0004 \| 10 \| nan \| \| 0.0 \| 0.0005 \| 15 \| nan \| \| 0.0 \| 0.0007 \| 20 \| nan \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
gokulsrinivasagan/bert_base_lda_20_v1_rte	gokulsrinivasagan	"2024-12-04T12:50:37Z"	107	0	transformers	[ "transformers", "tensorboard", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "en", "dataset:glue", "base_model:gokulsrinivasagan/bert_base_lda_20_v1", "base_model:finetune:gokulsrinivasagan/bert_base_lda_20_v1", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	"2024-11-26T19:23:31Z"	--- library_name: transformers language: - en base_model: gokulsrinivasagan/bert_base_lda_20_v1 tags: - generated_from_trainer datasets: - glue metrics: - accuracy model-index: - name: bert_base_lda_20_v1_rte results: - task: name: Text Classification type: text-classification dataset: name: GLUE RTE type: glue args: rte metrics: - name: Accuracy type: accuracy value: 0.5270758122743683 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # bert_base_lda_20_v1_rte This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_20_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_20_v1) on the GLUE RTE dataset. It achieves the following results on the evaluation set: - Loss: 0.6937 - Accuracy: 0.5271 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 256 - eval_batch_size: 256 - seed: 10 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 50 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 0.7289 \| 1.0 \| 10 \| 0.7114 \| 0.5415 \| \| 0.7107 \| 2.0 \| 20 \| 0.7287 \| 0.4729 \| \| 0.7029 \| 3.0 \| 30 \| 0.6961 \| 0.4693 \| \| 0.6982 \| 4.0 \| 40 \| 0.6937 \| 0.5271 \| \| 0.6891 \| 5.0 \| 50 \| 0.7067 \| 0.5343 \| \| 0.6843 \| 6.0 \| 60 \| 0.7118 \| 0.5090 \| \| 0.6558 \| 7.0 \| 70 \| 0.7532 \| 0.5054 \| \| 0.5694 \| 8.0 \| 80 \| 0.9040 \| 0.4982 \| \| 0.4815 \| 9.0 \| 90 \| 1.0390 \| 0.4549 \| ### Framework versions - Transformers 4.46.3 - Pytorch 2.2.1+cu118 - Datasets 2.17.0 - Tokenizers 0.20.3
megajajo/phi-1_5-finetuned	megajajo	"2024-05-04T19:50:04Z"	1	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:microsoft/phi-1_5", "base_model:adapter:microsoft/phi-1_5", "region:us" ]	null	"2024-05-03T20:49:37Z"	--- library_name: peft base_model: microsoft/phi-1_5 --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.10.0
alexeyGod/Test23	alexeyGod	"2025-03-14T03:15:07Z"	0	0	diffusers	[ "diffusers", "text-to-image", "lora", "template:diffusion-lora", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "license:apache-2.0", "region:us" ]	text-to-image	"2025-03-14T03:12:37Z"	--- tags: - text-to-image - lora - diffusers - template:diffusion-lora widget: - text: 'man TomBig, underwear,he is cooking ' parameters: negative_prompt: >- ng_deepnegative_v1_75t,(badhandv4:1.2),EasyNegative,(worst quality:2),,nsfw output: url: >- images/d902c4c08a06f43ba91a0728ebae4b0b846bbaae326d9b73d632f6ca92d0466f.png base_model: black-forest-labs/FLUX.1-dev instance_prompt: TomBig license: apache-2.0 --- # ggg <Gallery /> ## Trigger words You should use `TomBig` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/alexeyGod/Test23/tree/main) them in the Files & versions tab.
RedSparkie/PaulaPua	RedSparkie	"2025-03-06T00:04:28Z"	0	0	diffusers	[ "diffusers", "text-to-image", "stable-diffusion", "lora", "template:sd-lora", "migrated", "photorealistic", "sexy", "woman", "celebrity", "realistic", "influencer", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "license:other", "region:us" ]	text-to-image	"2025-03-05T23:55:35Z"	--- license: other license_name: bespoke-lora-trained-license license_link: >- https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=RentCivit&allowDerivatives=True&allowDifferentLicense=True tags: - text-to-image - stable-diffusion - lora - diffusers - template:sd-lora - migrated - photorealistic - sexy - woman - celebrity - realistic - influencer base_model: black-forest-labs/FLUX.1-dev instance_prompt: PaulaPua widget: - text: >- Posing for a LinkedIn profile picture. Expensive, black suit with white shirt. Red lipstick. Platinum blond hair. output: url: images/example_sq5sxnbnr.png --- [![Ko‑fi](https://ko-fi.com/img/githubbutton_sm.svg)](https://ko-fi.com/redsparkie)
lesso01/4fdc1db0-1091-49b7-aab5-4fce516ab3f9	lesso01	"2025-02-16T00:33:03Z"	0	0	peft	[ "peft", "safetensors", "opt", "axolotl", "generated_from_trainer", "base_model:facebook/opt-125m", "base_model:adapter:facebook/opt-125m", "license:other", "region:us" ]	null	"2025-02-15T23:55:29Z"	--- library_name: peft license: other base_model: facebook/opt-125m tags: - axolotl - generated_from_trainer model-index: - name: 4fdc1db0-1091-49b7-aab5-4fce516ab3f9 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <br> # 4fdc1db0-1091-49b7-aab5-4fce516ab3f9 This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on the None dataset. It achieves the following results on the evaluation set: - Loss: 2.1539 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.000201 - train_batch_size: 4 - eval_batch_size: 4 - seed: 10 - gradient_accumulation_steps: 2 - total_train_batch_size: 8 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 50 - training_steps: 500 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| No log \| 0.0000 \| 1 \| 2.9383 \| \| 4.6909 \| 0.0014 \| 50 \| 2.4425 \| \| 4.3 \| 0.0027 \| 100 \| 2.3725 \| \| 4.2006 \| 0.0041 \| 150 \| 2.3445 \| \| 4.0855 \| 0.0054 \| 200 \| 2.3015 \| \| 4.2416 \| 0.0068 \| 250 \| 2.3096 \| \| 4.1256 \| 0.0081 \| 300 \| 2.2099 \| \| 3.9752 \| 0.0095 \| 350 \| 2.1886 \| \| 4.1878 \| 0.0108 \| 400 \| 2.1623 \| \| 3.9657 \| 0.0122 \| 450 \| 2.1546 \| \| 4.0042 \| 0.0135 \| 500 \| 2.1539 \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
iManay/fil-bic-mt5b	iManay	"2024-05-29T06:05:11Z"	7	0	transformers	[ "transformers", "tf", "mt5", "text2text-generation", "generated_from_keras_callback", "base_model:google/mt5-base", "base_model:finetune:google/mt5-base", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text2text-generation	"2024-05-27T03:29:19Z"	--- license: apache-2.0 tags: - generated_from_keras_callback base_model: google/mt5-base model-index: - name: fil-bic-mt5b results: [] --- <!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. --> # fil-bic-mt5b This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.2155 - Validation Loss: 2.4691 - Epoch: 19 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 0.001, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01} - training_precision: float32 ### Training results \| Train Loss \| Validation Loss \| Epoch \| \|:----------:\|:---------------:\|:-----:\| \| 4.8782 \| 3.0764 \| 0 \| \| 3.0550 \| 2.4897 \| 1 \| \| 2.4361 \| 2.1678 \| 2 \| \| 2.0424 \| 1.9982 \| 3 \| \| 1.7454 \| 1.8860 \| 4 \| \| 1.5089 \| 1.8502 \| 5 \| \| 1.3137 \| 1.8682 \| 6 \| \| 1.1487 \| 1.8252 \| 7 \| \| 0.9793 \| 1.8486 \| 8 \| \| 0.8428 \| 1.8815 \| 9 \| \| 0.7107 \| 1.9716 \| 10 \| \| 0.6015 \| 2.0271 \| 11 \| \| 0.5106 \| 2.1239 \| 12 \| \| 0.4392 \| 2.2095 \| 13 \| \| 0.3786 \| 2.2045 \| 14 \| \| 0.3315 \| 2.2884 \| 15 \| \| 0.2882 \| 2.3419 \| 16 \| \| 0.2587 \| 2.4029 \| 17 \| \| 0.2354 \| 2.4173 \| 18 \| \| 0.2155 \| 2.4691 \| 19 \| ### Framework versions - Transformers 4.37.2 - TensorFlow 2.15.0 - Datasets 2.17.0 - Tokenizers 0.15.2
Larry2028/cn	Larry2028	"2024-02-07T12:28:42Z"	0	0	null	[ "license:bigscience-openrail-m", "region:us" ]	null	"2024-02-07T12:28:42Z"	--- license: bigscience-openrail-m ---
johnpaulbin/meme-titles	johnpaulbin	"2023-06-28T00:05:35Z"	178	1	transformers	[ "transformers", "pytorch", "safetensors", "gpt2", "text-generation", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2022-03-02T23:29:05Z"	Trained on ~400 youtube titles of meme compilations on youtube. WARNING: may produce offensive content.
Sneka/mistral-json-finetune	Sneka	"2023-11-21T13:03:58Z"	4	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "generated_from_trainer", "base_model:mistralai/Mistral-7B-v0.1", "base_model:finetune:mistralai/Mistral-7B-v0.1", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2023-11-21T12:17:50Z"	--- license: apache-2.0 base_model: mistralai/Mistral-7B-v0.1 tags: - generated_from_trainer model-index: - name: mistral-json-finetune results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # mistral-json-finetune This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.3730 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2.5e-05 - train_batch_size: 2 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 5 - training_steps: 1000 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 1.2986 \| 0.57 \| 50 \| 0.6897 \| \| 0.4469 \| 1.14 \| 100 \| 0.4239 \| \| 0.2978 \| 1.71 \| 150 \| 0.3497 \| \| 0.2279 \| 2.29 \| 200 \| 0.3126 \| \| 0.1869 \| 2.86 \| 250 \| 0.2858 \| \| 0.137 \| 3.43 \| 300 \| 0.2848 \| \| 0.1221 \| 4.0 \| 350 \| 0.2713 \| \| 0.0918 \| 4.57 \| 400 \| 0.2750 \| \| 0.0832 \| 5.14 \| 450 \| 0.2781 \| \| 0.0681 \| 5.71 \| 500 \| 0.2807 \| \| 0.055 \| 6.29 \| 550 \| 0.2902 \| \| 0.0515 \| 6.86 \| 600 \| 0.2746 \| \| 0.0463 \| 7.43 \| 650 \| 0.3078 \| \| 0.0421 \| 8.0 \| 700 \| 0.2971 \| \| 0.0354 \| 8.57 \| 750 \| 0.3196 \| \| 0.0276 \| 9.14 \| 800 \| 0.3490 \| \| 0.0281 \| 9.71 \| 850 \| 0.3411 \| \| 0.026 \| 10.29 \| 900 \| 0.3658 \| \| 0.0241 \| 10.86 \| 950 \| 0.3661 \| \| 0.0209 \| 11.43 \| 1000 \| 0.3730 \| ### Framework versions - Transformers 4.36.0.dev0 - Pytorch 2.1.1+cu121 - Datasets 2.15.0 - Tokenizers 0.15.0
AstraMindAI/xttsv2	AstraMindAI	"2024-12-04T15:10:04Z"	3,806	3	null	[ "xtts", "custom_code", "base_model:coqui/XTTS-v2", "base_model:finetune:coqui/XTTS-v2", "license:apache-2.0", "region:us" ]	null	"2024-10-24T09:46:49Z"	--- license: apache-2.0 base_model: - coqui/XTTS-v2 --- # Auralis 🌌 ## Model Details 🛠️ Model Name: Auralis Model Architecture: Based on [Coqui XTTS-v2](https://huggingface.co/coqui/XTTS-v2) License: - license: Apache 2.0 - base_model: XTTS-v2 Components [Coqui AI License](https://coqui.ai/cpml) Language Support: English, Spanish, French, German, Italian, Portuguese, Polish, Turkish, Russian, Dutch, Czech, Arabic, Chinese (Simplified), Hungarian, Korean, Japanese, Hindi Developed by: [AstraMind.ai](https://www.astramind.ai) GitHub: [AstraMind AI](https://github.com/astramind-ai/Auralis/tree/main) Primary Use Case: Text-to-Speech (TTS) generation for real-world applications, including books, dialogues, and multilingual tasks. --- ## Model Description 🚀 Auralis transforms text into natural, high-quality speech with exceptional speed and scalability. It is powered by [Coqui XTTS-v2](https://huggingface.co/coqui/XTTS-v2) and optimized for both consumer-grade and high-performance GPUs. Auralis is designed to meet real-world needs like long-text processing, voice cloning, and concurrent request handling. ### Key Features: - Warp-Speed Processing: Generate speech for an entire novel (e.g., Harry Potter) in ~10 minutes. - Hardware Friendly: Requires <10GB VRAM on a single NVIDIA RTX 3090. - Scalable: Handles multiple requests simultaneously. - Streaming: Seamlessly processes long texts in a streaming format. - Custom Voices: Enables voice cloning from short reference audio. --- ## Quick Start ⭐ ```python from auralis import TTS, TTSRequest # Initialize the model tts = TTS().from_pretrained("AstraMindAI/xtts2-gpt") # Create a TTS request request = TTSRequest( text="Hello Earth! This is Auralis speaking.", speaker_files=["reference.wav"] ) # Generate speech output = tts.generate_speech(request) output.save("output.wav") ``` --- ## Ebook Generation 📚 Auralis converting ebooks into audio formats at lightning speed. For Python script, check out [ebook_audio_generator.py](https://github.com/astramind-ai/Auralis/blob/main/examples/vocalize_a_ebook.py). ```python def process_book(chapter_file: str, speaker_file: str): # Read chapter with open(chapter_file, 'r') as f: chapter = f.read() # You can pass the whole book, auralis will take care of splitting request = TTSRequest( text=chapter, speaker_files=[speaker_file], audio_config=AudioPreprocessingConfig( enhance_speech=True, normalize=True ) ) output = tts.generate_speech(request) output.play() output.save("chapter_output.wav") # Example usage process_book("chapter1.txt", "reference_voice.wav") ``` --- ## Intended Use 🌟 Auralis is designed for: - Content Creators: Generate audiobooks, podcasts, or voiceovers. - Developers: Integrate TTS into applications via a simple Python API. - Accessibility: Providing audio versions of digital content for people with visual or reading difficulties. - Multilingual Scenarios: Convert text to speech in multiple supported languages. --- ## Performance 📊 Benchmarks on NVIDIA RTX 3090: - Short phrases (<100 characters): ~1 second - Medium texts (<1,000 characters): ~5-10 seconds - Full books (~100,000 characters): ~10 minutes Memory Usage: - Base VRAM: ~4GB - Peak VRAM: ~10GB --- ## Model Features 🛸 1. Speed & Efficiency: - Smart batching for rapid processing of long texts. - Memory-optimized for consumer GPUs. 2. Easy Integration: - Python API with support for synchronous and asynchronous workflows. - Streaming mode for continuous playback during generation. 3. Audio Quality Enhancements: - Background noise reduction. - Voice clarity and volume normalization. - Customizable audio preprocessing. 4. Multilingual Support: - Automatic language detection. - High-quality speech in 15+ languages. 5. Customization: - Voice cloning using short reference clips. - Adjustable parameters for tone, pacing, and language. --- ## Limitations & Ethical Considerations ⚠️ - Voice Cloning Risks: Auralis supports voice cloning, which may raise ethical concerns about misuse. Use responsibly and ensure proper consent. - Accent Limitations: While robust for many languages, accents and intonations may vary based on the input. --- ## Citation 📜 If you use Auralis in your research or projects, please cite: ```bibtex @misc{auralis2024, author = {AstraMind AI}, title = {Auralis: High-Performance Text-to-Speech Engine}, year = {2024}, url = {https://huggingface.co/AstraMindAI/auralis} } ```
kostiantynk1205/f41114b4-9f12-491d-bf4d-0b187dba056c	kostiantynk1205	"2025-02-01T00:09:21Z"	6	0	peft	[ "peft", "safetensors", "gpt_neox", "axolotl", "generated_from_trainer", "base_model:EleutherAI/pythia-1b", "base_model:adapter:EleutherAI/pythia-1b", "license:apache-2.0", "region:us" ]	null	"2025-01-31T23:49:46Z"	--- library_name: peft license: apache-2.0 base_model: EleutherAI/pythia-1b tags: - axolotl - generated_from_trainer model-index: - name: f41114b4-9f12-491d-bf4d-0b187dba056c results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.4.1` ```yaml adapter: lora base_model: EleutherAI/pythia-1b bf16: auto chat_template: llama3 dataset_prepared_path: null datasets: - data_files: - 774eb1c112fe248e_train_data.json ds_type: json format: custom path: /workspace/input_data/774eb1c112fe248e_train_data.json type: field_input: '' field_instruction: answer field_output: question format: '{instruction}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 128 eval_table_size: null evals_per_epoch: 4 flash_attention: false fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 4 gradient_checkpointing: false group_by_length: false hub_model_id: kostiantynk1205/f41114b4-9f12-491d-bf4d-0b187dba056c hub_repo: null hub_strategy: checkpoint hub_token: null learning_rate: 0.0002 load_in_4bit: false load_in_8bit: false local_rank: null logging_steps: 10 lora_alpha: 16 lora_dropout: 0.05 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 8 lora_target_linear: true lr_scheduler: cosine max_steps: 200 micro_batch_size: 2 mlflow_experiment_name: /tmp/774eb1c112fe248e_train_data.json model_type: AutoModelForCausalLM num_epochs: 1 optimizer: adamw_bnb_8bit output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false saves_per_epoch: 4 sequence_len: 512 special_tokens: pad_token: <\|endoftext\|> strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: 27bd5a7b-564b-47ce-bf71-ab73f604ca9e wandb_project: Birthday-SN56-23-Gradients-On-Demand wandb_run: your_name wandb_runid: 27bd5a7b-564b-47ce-bf71-ab73f604ca9e warmup_steps: 5 weight_decay: 0.0 xformers_attention: null ``` </details><br> # f41114b4-9f12-491d-bf4d-0b187dba056c This model is a fine-tuned version of [EleutherAI/pythia-1b](https://huggingface.co/EleutherAI/pythia-1b) on the None dataset. It achieves the following results on the evaluation set: - Loss: 2.4651 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 5 - training_steps: 200 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| No log \| 0.0000 \| 1 \| 4.0608 \| \| 10.5989 \| 0.0007 \| 50 \| 2.5510 \| \| 9.3417 \| 0.0014 \| 100 \| 2.4980 \| \| 10.5138 \| 0.0021 \| 150 \| 2.4703 \| \| 9.6977 \| 0.0028 \| 200 \| 2.4651 \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
dah1214/faset-perf-whisper-medium-tw	dah1214	"2024-02-20T17:36:35Z"	0	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:openai/whisper-large-v2", "base_model:adapter:openai/whisper-large-v2", "region:us" ]	null	"2024-02-19T02:56:46Z"	--- library_name: peft base_model: openai/whisper-large-v2 --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.8.2
huggingtweets/pfrazee	huggingtweets	"2021-05-22T18:33:55Z"	6	0	transformers	[ "transformers", "pytorch", "jax", "gpt2", "text-generation", "huggingtweets", "en", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2022-03-02T23:29:05Z"	--- language: en thumbnail: https://www.huggingtweets.com/pfrazee/1617856674100/predictions.png tags: - huggingtweets widget: - text: "My dream is" --- <div> <div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1302310345411887107/0LpHs9Rd_400x400.jpg')"> </div> <div style="margin-top: 8px; font-size: 19px; font-weight: 800">Paul Frazee✌️ 🤖 AI Bot </div> <div style="font-size: 15px">@pfrazee bot</div> </div> I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets). Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)! ## How does it work? The model uses the following pipeline. ![pipeline](https://github.com/borisdayma/huggingtweets/blob/master/img/pipeline.png?raw=true) To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI). ## Training data The model was trained on [@pfrazee's tweets](https://twitter.com/pfrazee). \| Data \| Quantity \| \| --- \| --- \| \| Tweets downloaded \| 3238 \| \| Retweets \| 334 \| \| Short tweets \| 237 \| \| Tweets kept \| 2667 \| [Explore the data](https://wandb.ai/wandb/huggingtweets/runs/134luj87/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline. ## Training procedure The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @pfrazee's tweets. Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/1ajilr7t) for full transparency and reproducibility. At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/1ajilr7t/artifacts) is logged and versioned. ## How to use You can use this model directly with a pipeline for text generation: ```python from transformers import pipeline generator = pipeline('text-generation', model='huggingtweets/pfrazee') generator("My dream is", num_return_sequences=5) ``` ## Limitations and bias The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias). In addition, the data present in the user's tweets further affects the text generated by the model. ## About Built by Boris Dayma [![Follow](https://img.shields.io/twitter/follow/borisdayma?style=social)](https://twitter.com/intent/follow?screen_name=borisdayma) For more details, visit the project repository. [![GitHub stars](https://img.shields.io/github/stars/borisdayma/huggingtweets?style=social)](https://github.com/borisdayma/huggingtweets)
Arkana08/LexiMaid-L3-8B	Arkana08	"2024-10-15T07:46:20Z"	10	2	transformers	[ "transformers", "safetensors", "llama", "text-generation", "mergekit", "merge", "conversational", "arxiv:2311.03099", "arxiv:2306.01708", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2024-10-13T05:04:14Z"	--- base_model: [] library_name: transformers tags: - mergekit - merge --- --- ### (GGUF) Thanks: #### mradermacher - GGUF: [mradermacher/LexiMaid-L3-8B-GGUF](https://huggingface.co/mradermacher/LexiMaid-L3-8B-GGUF) - imatrix GGUF: [mradermacher/LexiMaid-L3-8B-i1-GGUF](https://huggingface.co/mradermacher/LexiMaid-L3-8B-i1-GGUF) --- This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). --- Leximaid - This experimental model was created based on discussions on Reddit, where models such as [Lumimaid-v0.2-8B](https://huggingface.co/NeverSleep/Lumimaid-v0.2-8B), [Dusk_Rainbow](https://huggingface.co/SicariusSicariiStuff/Dusk_Rainbow), [Stheno-v3.4](https://huggingface.co/Sao10K/Llama-3.1-8B-Stheno-v3.4), [Celeste-V1.5](https://huggingface.co/nothingiisreal/L3.1-8B-Celeste-V1.5), and [Lexi-Uncensored-V2](https://huggingface.co/Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2) were mentioned — each with its own strengths and weaknesses. Some of them received criticism, which inspired me to create a new synthesis. To merge the models, I used the dare ties method, first combining [Lumimaid-v0.2-8B](https://huggingface.co/NeverSleep/Lumimaid-v0.2-8B), [Dusk_Rainbow](https://huggingface.co/SicariusSicariiStuff/Dusk_Rainbow), and [Stheno-v3.4](https://huggingface.co/Sao10K/Llama-3.1-8B-Stheno-v3.4), and then mixing the resulting model with [Celeste-V1.5](https://huggingface.co/nothingiisreal/L3.1-8B-Celeste-V1.5) and [Lexi-Uncensored-V2](https://huggingface.co/Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2). Leximaid is focused on roleplay and creative storytelling. --- ## Merge Details ### Merge Method This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708). ### Models Merged The following models were included in the merge: [Lumimaid-v0.2-8B](https://huggingface.co/NeverSleep/Lumimaid-v0.2-8B) [Dusk_Rainbow](https://huggingface.co/SicariusSicariiStuff/Dusk_Rainbow) [Stheno-v3.4](https://huggingface.co/Sao10K/Llama-3.1-8B-Stheno-v3.4) [Celeste-V1.5](https://huggingface.co/nothingiisreal/L3.1-8B-Celeste-V1.5) [Lexi-Uncensored-V2](https://huggingface.co/Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2) ## Configuration The following YAML configuration was used to produce Leximaid: ```yaml models: - model: Arkana08/Maxi-Fail-L3-8b parameters: weight: 0.4 density: 0.7 - model: nothingiisreal/L3.1-8B-Celeste-V1.5 parameters: weight: 0.3 density: 0.75 - model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2 parameters: weight: 0.3 density: 0.65 merge_method: dare_ties base_model: Arkana08/Maxi-Fail-L3-8b parameters: int8_mask: true dtype: bfloat16 ``` ## Credits Thanks to the creators of the models: - [NeverSleep/Lumimaid-v0.2-8B](https://huggingface.co/NeverSleep/Lumimaid-v0.2-8B) - [SicariusSicariiStuff/Dusk_Rainbow](https://huggingface.co/SicariusSicariiStuff/Dusk_Rainbow) - [Sao10K/Llama-3.1-8B-Stheno-v3.4](https://huggingface.co/Sao10K/Llama-3.1-8B-Stheno-v3.4) - [nothingiisreal/L3.1-8B-Celeste-V1.5](https://huggingface.co/nothingiisreal/L3.1-8B-Celeste-V1.5) - [Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2](https://huggingface.co/Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2)
hkufyp2024/binary-stock-classifier	hkufyp2024	"2024-04-22T09:25:49Z"	112	0	transformers	[ "transformers", "tensorboard", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	"2024-04-22T09:21:42Z"	--- license: apache-2.0 base_model: distilbert/distilbert-base-uncased tags: - generated_from_trainer metrics: - accuracy model-index: - name: binary-stock-classifier results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # binary-stock-classifier This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.1577 - Accuracy: 0.95 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 9 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| No log \| 1.0 \| 90 \| 0.0497 \| 1.0 \| \| No log \| 2.0 \| 180 \| 0.0138 \| 1.0 \| \| No log \| 3.0 \| 270 \| 0.4034 \| 0.9 \| \| No log \| 4.0 \| 360 \| 0.2492 \| 0.95 \| \| No log \| 5.0 \| 450 \| 0.1985 \| 0.95 \| \| 0.1536 \| 6.0 \| 540 \| 0.0427 \| 0.95 \| \| 0.1536 \| 7.0 \| 630 \| 0.2490 \| 0.95 \| \| 0.1536 \| 8.0 \| 720 \| 0.1568 \| 0.95 \| \| 0.1536 \| 9.0 \| 810 \| 0.1577 \| 0.95 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.15.2
mradermacher/Llama-3-neoAI-8B-Chat-v0.1-GGUF	mradermacher	"2024-06-26T14:38:50Z"	246	1	transformers	[ "transformers", "gguf", "ja", "en", "base_model:neoai-inc/Llama-3-neoAI-8B-Chat-v0.1", "base_model:quantized:neoai-inc/Llama-3-neoAI-8B-Chat-v0.1", "license:llama3", "endpoints_compatible", "region:us", "conversational" ]	null	"2024-06-26T14:08:14Z"	--- base_model: neoai-inc/Llama-3-neoAI-8B-Chat-v0.1 language: - ja - en library_name: transformers license: llama3 quantized_by: mradermacher --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/neoai-inc/Llama-3-neoAI-8B-Chat-v0.1 <!-- provided-files --> weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3-neoAI-8B-Chat-v0.1-i1-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-neoAI-8B-Chat-v0.1-GGUF/resolve/main/Llama-3-neoAI-8B-Chat-v0.1.Q2_K.gguf) \| Q2_K \| 3.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-neoAI-8B-Chat-v0.1-GGUF/resolve/main/Llama-3-neoAI-8B-Chat-v0.1.IQ3_XS.gguf) \| IQ3_XS \| 3.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-neoAI-8B-Chat-v0.1-GGUF/resolve/main/Llama-3-neoAI-8B-Chat-v0.1.Q3_K_S.gguf) \| Q3_K_S \| 3.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-neoAI-8B-Chat-v0.1-GGUF/resolve/main/Llama-3-neoAI-8B-Chat-v0.1.IQ3_S.gguf) \| IQ3_S \| 3.8 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-neoAI-8B-Chat-v0.1-GGUF/resolve/main/Llama-3-neoAI-8B-Chat-v0.1.IQ3_M.gguf) \| IQ3_M \| 3.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-neoAI-8B-Chat-v0.1-GGUF/resolve/main/Llama-3-neoAI-8B-Chat-v0.1.Q3_K_M.gguf) \| Q3_K_M \| 4.1 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-neoAI-8B-Chat-v0.1-GGUF/resolve/main/Llama-3-neoAI-8B-Chat-v0.1.Q3_K_L.gguf) \| Q3_K_L \| 4.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-neoAI-8B-Chat-v0.1-GGUF/resolve/main/Llama-3-neoAI-8B-Chat-v0.1.IQ4_XS.gguf) \| IQ4_XS \| 4.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-neoAI-8B-Chat-v0.1-GGUF/resolve/main/Llama-3-neoAI-8B-Chat-v0.1.Q4_K_S.gguf) \| Q4_K_S \| 4.8 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-neoAI-8B-Chat-v0.1-GGUF/resolve/main/Llama-3-neoAI-8B-Chat-v0.1.Q4_K_M.gguf) \| Q4_K_M \| 5.0 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-neoAI-8B-Chat-v0.1-GGUF/resolve/main/Llama-3-neoAI-8B-Chat-v0.1.Q5_K_S.gguf) \| Q5_K_S \| 5.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-neoAI-8B-Chat-v0.1-GGUF/resolve/main/Llama-3-neoAI-8B-Chat-v0.1.Q5_K_M.gguf) \| Q5_K_M \| 5.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-neoAI-8B-Chat-v0.1-GGUF/resolve/main/Llama-3-neoAI-8B-Chat-v0.1.Q6_K.gguf) \| Q6_K \| 6.7 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-neoAI-8B-Chat-v0.1-GGUF/resolve/main/Llama-3-neoAI-8B-Chat-v0.1.Q8_0.gguf) \| Q8_0 \| 8.6 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-neoAI-8B-Chat-v0.1-GGUF/resolve/main/Llama-3-neoAI-8B-Chat-v0.1.f16.gguf) \| f16 \| 16.2 \| 16 bpw, overkill \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
mradermacher/Dolphin-5.1-7b-i1-GGUF	mradermacher	"2025-01-24T12:08:07Z"	575	1	transformers	[ "transformers", "gguf", "merge", "mergekit", "lazymergekit", "cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser", "teknium/OpenHermes-2.5-Mistral-7B", "en", "base_model:Isotonic/Dolphin-5.1-7b", "base_model:quantized:Isotonic/Dolphin-5.1-7b", "license:apache-2.0", "endpoints_compatible", "region:us", "imatrix" ]	null	"2025-01-24T11:11:28Z"	--- base_model: Isotonic/Dolphin-5.1-7b language: - en library_name: transformers license: apache-2.0 quantized_by: mradermacher tags: - merge - mergekit - lazymergekit - cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser - teknium/OpenHermes-2.5-Mistral-7B --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/Isotonic/Dolphin-5.1-7b <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/Dolphin-5.1-7b-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/Dolphin-5.1-7b-i1-GGUF/resolve/main/Dolphin-5.1-7b.i1-IQ1_S.gguf) \| i1-IQ1_S \| 1.7 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/Dolphin-5.1-7b-i1-GGUF/resolve/main/Dolphin-5.1-7b.i1-IQ1_M.gguf) \| i1-IQ1_M \| 1.9 \| mostly desperate \| \| [GGUF](https://huggingface.co/mradermacher/Dolphin-5.1-7b-i1-GGUF/resolve/main/Dolphin-5.1-7b.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 2.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/Dolphin-5.1-7b-i1-GGUF/resolve/main/Dolphin-5.1-7b.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 2.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/Dolphin-5.1-7b-i1-GGUF/resolve/main/Dolphin-5.1-7b.i1-IQ2_S.gguf) \| i1-IQ2_S \| 2.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Dolphin-5.1-7b-i1-GGUF/resolve/main/Dolphin-5.1-7b.i1-IQ2_M.gguf) \| i1-IQ2_M \| 2.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Dolphin-5.1-7b-i1-GGUF/resolve/main/Dolphin-5.1-7b.i1-Q2_K_S.gguf) \| i1-Q2_K_S \| 2.6 \| very low quality \| \| [GGUF](https://huggingface.co/mradermacher/Dolphin-5.1-7b-i1-GGUF/resolve/main/Dolphin-5.1-7b.i1-Q2_K.gguf) \| i1-Q2_K \| 2.8 \| IQ3_XXS probably better \| \| [GGUF](https://huggingface.co/mradermacher/Dolphin-5.1-7b-i1-GGUF/resolve/main/Dolphin-5.1-7b.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 2.9 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Dolphin-5.1-7b-i1-GGUF/resolve/main/Dolphin-5.1-7b.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 3.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/Dolphin-5.1-7b-i1-GGUF/resolve/main/Dolphin-5.1-7b.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 3.3 \| IQ3_XS probably better \| \| [GGUF](https://huggingface.co/mradermacher/Dolphin-5.1-7b-i1-GGUF/resolve/main/Dolphin-5.1-7b.i1-IQ3_S.gguf) \| i1-IQ3_S \| 3.3 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/Dolphin-5.1-7b-i1-GGUF/resolve/main/Dolphin-5.1-7b.i1-IQ3_M.gguf) \| i1-IQ3_M \| 3.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Dolphin-5.1-7b-i1-GGUF/resolve/main/Dolphin-5.1-7b.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 3.6 \| IQ3_S probably better \| \| [GGUF](https://huggingface.co/mradermacher/Dolphin-5.1-7b-i1-GGUF/resolve/main/Dolphin-5.1-7b.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 3.9 \| IQ3_M probably better \| \| [GGUF](https://huggingface.co/mradermacher/Dolphin-5.1-7b-i1-GGUF/resolve/main/Dolphin-5.1-7b.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 4.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/Dolphin-5.1-7b-i1-GGUF/resolve/main/Dolphin-5.1-7b.i1-Q4_0.gguf) \| i1-Q4_0 \| 4.2 \| fast, low quality \| \| [GGUF](https://huggingface.co/mradermacher/Dolphin-5.1-7b-i1-GGUF/resolve/main/Dolphin-5.1-7b.i1-IQ4_NL.gguf) \| i1-IQ4_NL \| 4.2 \| prefer IQ4_XS \| \| [GGUF](https://huggingface.co/mradermacher/Dolphin-5.1-7b-i1-GGUF/resolve/main/Dolphin-5.1-7b.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 4.2 \| optimal size/speed/quality \| \| [GGUF](https://huggingface.co/mradermacher/Dolphin-5.1-7b-i1-GGUF/resolve/main/Dolphin-5.1-7b.i1-Q4_K_M.gguf) \| i1-Q4_K_M \| 4.5 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Dolphin-5.1-7b-i1-GGUF/resolve/main/Dolphin-5.1-7b.i1-Q4_1.gguf) \| i1-Q4_1 \| 4.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/Dolphin-5.1-7b-i1-GGUF/resolve/main/Dolphin-5.1-7b.i1-Q5_K_S.gguf) \| i1-Q5_K_S \| 5.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/Dolphin-5.1-7b-i1-GGUF/resolve/main/Dolphin-5.1-7b.i1-Q5_K_M.gguf) \| i1-Q5_K_M \| 5.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/Dolphin-5.1-7b-i1-GGUF/resolve/main/Dolphin-5.1-7b.i1-Q6_K.gguf) \| i1-Q6_K \| 6.0 \| practically like static Q6_K \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. <!-- end -->
ZeroWw/Yi-1.5-9B-32K-GGUF	ZeroWw	"2024-06-25T14:37:00Z"	11	1	null	[ "gguf", "en", "license:mit", "endpoints_compatible", "region:us" ]	null	"2024-06-25T14:19:16Z"	--- license: mit language: - en --- My own (ZeroWw) quantizations. output and embed tensors quantized to f16. all other tensors quantized to q5_k or q6_k. Result: both f16.q6 and f16.q5 are smaller than q8_0 standard quantization and they perform as well as the pure f16.
TroyDoesAI/MermaidMoE-15B	TroyDoesAI	"2024-04-12T01:59:24Z"	4	0	transformers	[ "transformers", "safetensors", "mixtral", "text-generation", "license:cc-by-4.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2024-04-07T16:37:31Z"	--- license: cc-by-4.0 --- THIS MODEL IS A SELF MERGE WITH NO FURTHER TRAINING FOR EVALUATION OF THE EFFECTS OF PRUNED MODELS MERGED TOGETHER IN A SELF MERGE.
HunyStark/ppo-LunarLander-v2	HunyStark	"2023-12-26T02:06:11Z"	0	0	stable-baselines3	[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	"2023-12-26T02:05:52Z"	--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 259.33 +/- 20.62 name: mean_reward verified: false --- # PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
BogdanTurbal/model_gpt2_medium_d_hate_bias_political_bias_ep_1_3_a_sqn_a_b_p_100_5_v_10	BogdanTurbal	"2024-08-11T20:21:45Z"	6	0	null	[ "tensorboard", "safetensors", "gpt2", "generated_from_trainer", "base_model:BogdanTurbal/model_gpt2_medium_d_hate_bias_ep_1_sqn_a_p_100_v_10", "base_model:finetune:BogdanTurbal/model_gpt2_medium_d_hate_bias_ep_1_sqn_a_p_100_v_10", "license:mit", "region:us" ]	null	"2024-08-11T19:49:58Z"	--- license: mit base_model: BogdanTurbal/model_gpt2_medium_d_hate_bias_ep_1_sqn_a_p_100_v_10 tags: - generated_from_trainer metrics: - accuracy model-index: - name: model_gpt2_medium_d_hate_bias_political_bias_ep_1_3_a_sqn_a_b_p_100_5_v_10 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # model_gpt2_medium_d_hate_bias_political_bias_ep_1_3_a_sqn_a_b_p_100_5_v_10 This model is a fine-tuned version of [BogdanTurbal/model_gpt2_medium_d_hate_bias_ep_1_sqn_a_p_100_v_10](https://huggingface.co/BogdanTurbal/model_gpt2_medium_d_hate_bias_ep_1_sqn_a_p_100_v_10) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.8600 - Accuracy: 0.7045 - F1 Micro: 0.7045 - Auc: 0.7730 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 16 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| F1 Micro \| Auc \| \|:-------------:\|:------:\|:----:\|:---------------:\|:--------:\|:--------:\|:------:\| \| 0.7866 \| 0.2703 \| 10 \| 0.6437 \| 0.6306 \| 0.6306 \| 0.6997 \| \| 0.6471 \| 0.5405 \| 20 \| 0.6366 \| 0.6452 \| 0.6452 \| 0.7367 \| \| 0.6642 \| 0.8108 \| 30 \| 0.5960 \| 0.6787 \| 0.6787 \| 0.7630 \| \| 0.622 \| 1.0811 \| 40 \| 0.6366 \| 0.6564 \| 0.6564 \| 0.7646 \| \| 0.4354 \| 1.3514 \| 50 \| 0.6507 \| 0.6718 \| 0.6718 \| 0.7571 \| \| 0.414 \| 1.6216 \| 60 \| 0.6929 \| 0.6804 \| 0.6804 \| 0.7575 \| \| 0.4344 \| 1.8919 \| 70 \| 0.6345 \| 0.7010 \| 0.7010 \| 0.7744 \| \| 0.2969 \| 2.1622 \| 80 \| 0.6606 \| 0.7045 \| 0.7045 \| 0.7788 \| \| 0.2133 \| 2.4324 \| 90 \| 0.7549 \| 0.7027 \| 0.7027 \| 0.7746 \| \| 0.1031 \| 2.7027 \| 100 \| 0.8532 \| 0.6942 \| 0.6942 \| 0.7743 \| \| 0.1658 \| 2.9730 \| 110 \| 0.8600 \| 0.7045 \| 0.7045 \| 0.7730 \| ### Framework versions - Transformers 4.44.0 - Pytorch 2.3.1+cu121 - Datasets 2.20.0 - Tokenizers 0.19.1
Shero448/EvelynZZZ-ilu	Shero448	"2025-03-27T20:51:08Z"	0	0	diffusers	[ "diffusers", "text-to-image", "lora", "template:diffusion-lora", "base_model:John6666/ilustrealmix-v20-sdxl", "base_model:adapter:John6666/ilustrealmix-v20-sdxl", "region:us" ]	text-to-image	"2025-03-27T20:50:55Z"	--- tags: - text-to-image - lora - diffusers - template:diffusion-lora widget: - text: >- masterpiece, best quality, in cafe, pizza on the table, chair, amazing quality, very aesthetic, absurdres, best quality, 4k, upscale, EvelynZZZ, 1girl, solo, sitting, eating, yummy, looking at viewer, blonde hair, hair bun, french braid, mole under eye, black choker, looking at viewer, purple eyes, short hair, closed mouth, jewelry, white shirt, hair between eyes, earrings, hair intakes, black jacket, large breasts, black gloves, sleeveless shirt, yellow necktie, black pants, high-waist pants, collared shirt, elbow gloves, thigh strap, bare shoulders, jacket on shoulders BREAK heart <lora:EvelynZZZ_ILv5:0.8> parameters: negative_prompt: >- pubic hair, 3d, cropped, loli, censored, (simple background:1.0), bar censoring, mosaic censoring, siblings, bad legs, clones, monochrome, clones, sketch, rought lines, patreon username, logo, bad proportions, artist signature, artist name, english text, text, korean text, speech bubble, sound effects, multiple views, 4koma,comics, comic, output: url: images/2025-02-28-175514_hassakuXLIllustrious_v13StyleA_448.png base_model: John6666/ilustrealmix-v20-sdxl instance_prompt: EvelynZZZ --- # EvelynZZZ-ilu <Gallery /> ## Trigger words You should use `EvelynZZZ` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/Shero448/EvelynZZZ-ilu/tree/main) them in the Files & versions tab.
LyliaEngine/Sinozick_Style_XL_Pony	LyliaEngine	"2024-05-31T09:46:52Z"	92	1	diffusers	[ "diffusers", "text-to-image", "stable-diffusion", "lora", "template:sd-lora", "base_model:LyliaEngine/Pony_Diffusion_V6_XL", "base_model:adapter:LyliaEngine/Pony_Diffusion_V6_XL", "license:cdla-permissive-2.0", "region:us" ]	text-to-image	"2024-05-31T09:44:35Z"	--- tags: - text-to-image - stable-diffusion - lora - diffusers - template:sd-lora widget: - text: >- (score_9, score_8_up), score_7_up, zPDXL, 1girl, upper body, black mantle, earrings, cyberpunk, eyepatch, neon eyepatch, black hair, wild hair, long hair, red eyes, looking at viewer, expressionless, dark, dark theme, black sclera, konohagakure symbol, forehead protector, naruto \(series\), <lora:Sinozick_Style_XL_Pony:1>, sinozick style parameters: negative_prompt: >- (extra fingers, deformed hands, polydactyl:1.1), (worst quality, low quality:1.2), bad quality, shiny, blurry, artists signature, (multiple tails), nuzzle, censored, pixelated, zPDXL-neg, pointy ears, output: url: images/00012-3760017729.jpeg - text: >- (score_9, score_8_up), score_7_up, zPDXL, 1girl, white hair, short hair, white eyes, mouth mask, looking at viewer, white kimono, red background, film grain, cowboy shot <lora:Sinozick_Style_XL_Pony:1>, sinozick style parameters: negative_prompt: >- (extra fingers, deformed hands, polydactyl:1.1), (worst quality, low quality:1.2), bad quality, shiny, blurry, artists signature, (multiple tails), nuzzle, censored, pixelated, zPDXL-neg, pointy ears, output: url: images/00019-46392353.jpeg base_model: LyliaEngine/Pony_Diffusion_V6_XL instance_prompt: sinozick style, flat color, dark theme license: cdla-permissive-2.0 --- # Sinozick_Style_XL_Pony <Gallery /> ## Model description Sinozick is an AI artist on Twitter I like a lot, the style he gets for his images is incredible, and I wanted to reproduce the best I could this style. I think he uses MidJourney, and SD can't replicate it very well, but I'm satisfied enough with it. One flaw ; It's better for OCs, using it with pre-made characters can reduce the impact of the style. Activation Prompt : sinozick style Helpful prompt Prompt : dark theme, flat color If you enjoyed this LoRA, think about leaving a like and post some images ! Thanks ! <3 ## Source https://civitai.com/models/432483/sinozick-style-or-style-lora-or-pony ## Credit https://civitai.com/user/LennonAI ## Trigger words You should use `sinozick style` to trigger the image generation. You should use `flat color` to trigger the image generation. You should use `dark theme` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/LyliaEngine/Sinozick_Style_XL_Pony/tree/main) them in the Files & versions tab.
Mimita6654/test	Mimita6654	"2022-07-02T07:47:08Z"	3	0	transformers	[ "transformers", "pytorch", "tensorboard", "bert", "fill-mask", "generated_from_trainer", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	"2022-07-02T07:44:21Z"	--- license: mit tags: - generated_from_trainer model-index: - name: test results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # test This model is a fine-tuned version of [prajjwal1/bert-small](https://huggingface.co/prajjwal1/bert-small) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 64 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10 ### Training results ### Framework versions - Transformers 4.18.0 - Pytorch 1.11.0 - Datasets 2.1.0 - Tokenizers 0.12.1
systemk/estimation-helpsteer-gemma-2-2b	systemk	"2025-03-27T05:42:02Z"	0	0	peft	[ "peft", "tensorboard", "safetensors", "generated_from_trainer", "base_model:google/gemma-2-2b-jpn-it", "base_model:adapter:google/gemma-2-2b-jpn-it", "license:gemma", "region:us" ]	null	"2025-03-27T05:41:57Z"	--- library_name: peft license: gemma base_model: google/gemma-2-2b-jpn-it tags: - generated_from_trainer model-index: - name: gemma-2-2b-evaluator-v2 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # gemma-2-2b-evaluator-v2 This model is a fine-tuned version of [google/gemma-2-2b-jpn-it](https://huggingface.co/google/gemma-2-2b-jpn-it) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.8410 - Helpfulness Accuracy: 0.5109 - Helpfulness Spearmanr: 0.5327 - Helpfulness Kendalltau: 0.3736 - Helpfulness Pearsonr: 0.5339 - Helpfulness Rmse: 0.5903 - Helpfulness Mae: 0.4713 - Correctness Accuracy: 0.6014 - Correctness Spearmanr: 0.5531 - Correctness Kendalltau: 0.3943 - Correctness Pearsonr: 0.5859 - Correctness Rmse: 0.5292 - Correctness Mae: 0.4221 - Coherence Accuracy: 0.6998 - Coherence Spearmanr: 0.4640 - Coherence Kendalltau: 0.3232 - Coherence Pearsonr: 0.4909 - Coherence Rmse: 0.5011 - Coherence Mae: 0.4405 - Complexity Accuracy: 0.6064 - Complexity Spearmanr: -0.0021 - Complexity Kendalltau: -0.0026 - Complexity Pearsonr: -0.0076 - Complexity Rmse: 0.3605 - Complexity Mae: 0.3205 - Verbosity Accuracy: 0.6362 - Verbosity Spearmanr: 0.4071 - Verbosity Kendalltau: 0.2757 - Verbosity Pearsonr: 0.3365 - Verbosity Rmse: 0.3724 - Verbosity Mae: 0.3068 - Avg Accuracy: 0.6109 - Avg Spearmanr: 0.3910 - Avg Kendalltau: 0.2728 - Avg Pearsonr: 0.3879 - Avg Rmse: 0.4707 - Avg Mae: 0.3922 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 2 - eval_batch_size: 16 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine_with_min_lr - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 1.0 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Helpfulness Accuracy \| Helpfulness Spearmanr \| Helpfulness Kendalltau \| Helpfulness Pearsonr \| Helpfulness Rmse \| Helpfulness Mae \| Correctness Accuracy \| Correctness Spearmanr \| Correctness Kendalltau \| Correctness Pearsonr \| Correctness Rmse \| Correctness Mae \| Coherence Accuracy \| Coherence Spearmanr \| Coherence Kendalltau \| Coherence Pearsonr \| Coherence Rmse \| Coherence Mae \| Complexity Accuracy \| Complexity Spearmanr \| Complexity Kendalltau \| Complexity Pearsonr \| Complexity Rmse \| Complexity Mae \| Verbosity Accuracy \| Verbosity Spearmanr \| Verbosity Kendalltau \| Verbosity Pearsonr \| Verbosity Rmse \| Verbosity Mae \| Avg Accuracy \| Avg Spearmanr \| Avg Kendalltau \| Avg Pearsonr \| Avg Rmse \| Avg Mae \| \|:-------------:\|:------:\|:----:\|:---------------:\|:--------------------:\|:---------------------:\|:----------------------:\|:--------------------:\|:----------------:\|:---------------:\|:--------------------:\|:---------------------:\|:----------------------:\|:--------------------:\|:----------------:\|:---------------:\|:------------------:\|:-------------------:\|:--------------------:\|:------------------:\|:--------------:\|:-------------:\|:-------------------:\|:--------------------:\|:---------------------:\|:-------------------:\|:---------------:\|:--------------:\|:------------------:\|:-------------------:\|:--------------------:\|:------------------:\|:--------------:\|:-------------:\|:------------:\|:-------------:\|:--------------:\|:------------:\|:--------:\|:-------:\| \| No log \| 0 \| 0 \| 6.0772 \| 0.3807 \| 0.0234 \| 0.0151 \| 0.0297 \| 0.9409 \| 0.7463 \| 0.1471 \| 0.0071 \| 0.0048 \| 0.0298 \| 1.3459 \| 1.1590 \| 0.3698 \| 0.0093 \| 0.0059 \| 0.0060 \| 1.2779 \| 1.0608 \| 0.0258 \| -0.0438 \| -0.0291 \| -0.0464 \| 2.1264 \| 1.9972 \| 0.3698 \| -0.0471 \| -0.0310 \| -0.0500 \| 1.0197 \| 0.7998 \| 0.2586 \| -0.0102 \| -0.0069 \| -0.0062 \| 1.3422 \| 1.1526 \| \| 1.2731 \| 0.2094 \| 500 \| 1.2058 \| 0.4404 \| 0.1512 \| 0.0986 \| 0.1462 \| 0.7513 \| 0.6121 \| 0.5338 \| 0.1290 \| 0.0836 \| 0.1806 \| 0.6719 \| 0.5388 \| 0.6700 \| 0.1137 \| 0.0764 \| 0.1443 \| 0.5356 \| 0.4510 \| 0.6054 \| -0.2206 \| -0.1464 \| -0.0710 \| 0.4624 \| 0.4287 \| 0.6243 \| 0.0942 \| 0.0622 \| -0.0191 \| 0.4919 \| 0.4087 \| 0.5748 \| 0.0535 \| 0.0349 \| 0.0762 \| 0.5826 \| 0.4878 \| \| 0.9212 \| 0.4188 \| 1000 \| 0.9210 \| 0.4980 \| 0.4385 \| 0.3020 \| 0.4357 \| 0.5932 \| 0.4747 \| 0.5944 \| 0.4142 \| 0.2897 \| 0.4702 \| 0.5473 \| 0.4357 \| 0.7068 \| 0.3103 \| 0.2104 \| 0.3688 \| 0.4894 \| 0.4244 \| 0.6054 \| -0.2491 \| -0.1664 \| -0.2532 \| 0.4269 \| 0.3880 \| 0.6362 \| 0.2771 \| 0.1860 \| 0.1669 \| 0.3959 \| 0.3246 \| 0.6082 \| 0.2382 \| 0.1643 \| 0.2377 \| 0.4905 \| 0.4095 \| \| 0.8859 \| 0.6283 \| 1500 \| 0.8554 \| 0.4911 \| 0.5129 \| 0.3572 \| 0.5111 \| 0.5972 \| 0.4769 \| 0.5755 \| 0.5366 \| 0.3813 \| 0.5659 \| 0.5430 \| 0.4334 \| 0.6958 \| 0.4329 \| 0.3006 \| 0.4621 \| 0.5038 \| 0.4418 \| 0.6054 \| -0.1199 \| -0.0813 \| -0.1286 \| 0.3882 \| 0.3489 \| 0.6362 \| 0.3749 \| 0.2544 \| 0.2937 \| 0.3931 \| 0.3275 \| 0.6008 \| 0.3475 \| 0.2424 \| 0.3409 \| 0.4851 \| 0.4057 \| \| 0.7737 \| 0.8377 \| 2000 \| 0.8410 \| 0.5109 \| 0.5327 \| 0.3736 \| 0.5339 \| 0.5903 \| 0.4713 \| 0.6014 \| 0.5531 \| 0.3943 \| 0.5859 \| 0.5292 \| 0.4221 \| 0.6998 \| 0.4640 \| 0.3232 \| 0.4909 \| 0.5011 \| 0.4405 \| 0.6064 \| -0.0021 \| -0.0026 \| -0.0076 \| 0.3605 \| 0.3205 \| 0.6362 \| 0.4071 \| 0.2757 \| 0.3365 \| 0.3724 \| 0.3068 \| 0.6109 \| 0.3910 \| 0.2728 \| 0.3879 \| 0.4707 \| 0.3922 \| ### Framework versions - PEFT 0.15.0 - Transformers 4.50.1 - Pytorch 2.6.0+cu124 - Datasets 3.4.1 - Tokenizers 0.21.1
BEE-spoke-data/TinyLlama-1.1bee	BEE-spoke-data	"2024-01-07T03:55:10Z"	18	1	transformers	[ "transformers", "safetensors", "llama", "text-generation", "bees", "beekeeping", "honey", "en", "dataset:BEE-spoke-data/bees-internal", "base_model:TinyLlama/TinyLlama-1.1B-intermediate-step-240k-503b", "base_model:finetune:TinyLlama/TinyLlama-1.1B-intermediate-step-240k-503b", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2023-09-19T22:30:43Z"	--- license: apache-2.0 base_model: PY007/TinyLlama-1.1B-intermediate-step-240k-503b tags: - bees - beekeeping - honey metrics: - accuracy inference: parameters: max_new_tokens: 64 do_sample: true renormalize_logits: true repetition_penalty: 1.05 no_repeat_ngram_size: 6 temperature: 0.9 top_p: 0.95 epsilon_cutoff: 0.0008 widget: - text: In beekeeping, the term "queen excluder" refers to example_title: Queen Excluder - text: One way to encourage a honey bee colony to produce more honey is by example_title: Increasing Honey Production - text: The lifecycle of a worker bee consists of several stages, starting with example_title: Lifecycle of a Worker Bee - text: Varroa destructor is a type of mite that example_title: Varroa Destructor - text: In the world of beekeeping, the acronym PPE stands for example_title: Beekeeping PPE - text: The term "robbing" in beekeeping refers to the act of example_title: Robbing in Beekeeping - text: \|- Question: What's the primary function of drone bees in a hive? Answer: example_title: Role of Drone Bees - text: To harvest honey from a hive, beekeepers often use a device known as a example_title: Honey Harvesting Device - text: >- Problem: You have a hive that produces 60 pounds of honey per year. You decide to split the hive into two. Assuming each hive now produces at a 70% rate compared to before, how much honey will you get from both hives next year? To calculate example_title: Beekeeping Math Problem - text: In beekeeping, "swarming" is the process where example_title: Swarming pipeline_tag: text-generation datasets: - BEE-spoke-data/bees-internal language: - en --- # TinyLlama-1.1bee 🐝 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/60bccec062080d33f875cd0c/vgDfbjic0S3OJwv9BNzQN.png) As we feverishly hit the refresh button on hf.co's homepage, on the hunt for the newest waifu chatbot to grace the AI stage, an epiphany struck us like a bee sting. What could we offer to the hive-mind of the community? The answer was as clear as honey—beekeeping, naturally. And thus, this un-bee-lievable model was born. ## Details This model is a fine-tuned version of [PY007/TinyLlama-1.1B-intermediate-step-240k-503b](https://huggingface.co/PY007/TinyLlama-1.1B-intermediate-step-240k-503b) on the `BEE-spoke-data/bees-internal` dataset. It achieves the following results on the evaluation set: - Loss: 2.4285 - Accuracy: 0.4969 ``` *** eval metrics * eval_accuracy = 0.4972 eval_loss = 2.4283 eval_runtime = 0:00:53.12 eval_samples = 239 eval_samples_per_second = 4.499 eval_steps_per_second = 1.129 perplexity = 11.3391 ``` ## 📜 Intended Uses & Limitations 📜 ### Intended Uses: 1. Educational Engagement: Whether you're a novice beekeeper, an enthusiast, or someone just looking to understand the buzz around bees, this model aims to serve as an informative and entertaining resource. 2. General Queries: Have questions about hive management, bee species, or honey extraction? Feel free to consult the model for general insights. 3. Academic & Research Inspiration: If you're diving into the world of apiculture studies or environmental science, our model could offer some preliminary insights and ideas. ### Limitations: 1. Not a Beekeeping Expert: As much as we admire bees and their hard work, this model is not a certified apiculturist. Please consult professional beekeeping resources or experts for serious decisions related to hive management, bee health, and honey production. 2. Licensing: Apache-2.0, following TinyLlama 3. Infallibility: Our model can err, just like any other piece of technology (or bee). Always double-check the information before applying it to your own hive or research. 4. Ethical Constraints**: This model may not be used for any illegal or unethical activities, including but not limited to: bioterrorism & standard terrorism, harassment, or spreading disinformation. ## Training and evaluation data While the full dataset is not yet complete and therefore not yet released for "safety reasons", you can check out a preliminary sample at: [bees-v0](https://huggingface.co/datasets/BEE-spoke-data/bees-v0) ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 4 - eval_batch_size: 4 - seed: 80085 - gradient_accumulation_steps: 8 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.03 - num_epochs: 2.0 # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_BEE-spoke-data__TinyLlama-1.1bee) \| Metric \| Value \| \|-----------------------\|---------------------------\| \| Avg. \| 29.15 \| \| ARC (25-shot) \| 30.55 \| \| HellaSwag (10-shot) \| 51.8 \| \| MMLU (5-shot) \| 24.25 \| \| TruthfulQA (0-shot) \| 39.01 \| \| Winogrande (5-shot) \| 54.46 \| \| GSM8K (5-shot) \| 0.23 \| \| DROP (3-shot) \| 3.74 \|
TheBlueObserver/SmolLM2-1.7B-Instruct-MLX-393a7	TheBlueObserver	"2024-12-20T10:45:33Z"	76	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "onnx", "transformers.js", "mlx", "conversational", "en", "base_model:HuggingFaceTB/SmolLM2-1.7B-Instruct", "base_model:quantized:HuggingFaceTB/SmolLM2-1.7B-Instruct", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "8-bit", "region:us" ]	text-generation	"2024-12-20T10:44:42Z"	--- base_model: HuggingFaceTB/SmolLM2-1.7B-Instruct language: - en library_name: transformers license: apache-2.0 pipeline_tag: text-generation tags: - safetensors - onnx - transformers.js - mlx --- # TheBlueObserver/SmolLM2-1.7B-Instruct-MLX-393a7 The Model [TheBlueObserver/SmolLM2-1.7B-Instruct-MLX-393a7](https://huggingface.co/TheBlueObserver/SmolLM2-1.7B-Instruct-MLX-393a7) was converted to MLX format from [HuggingFaceTB/SmolLM2-1.7B-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct) using mlx-lm version 0.20.2. ## Use with mlx ```bash pip install mlx-lm ``` ```python from mlx_lm import load, generate model, tokenizer = load("TheBlueObserver/SmolLM2-1.7B-Instruct-MLX-393a7") prompt="hello" if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None: messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) response = generate(model, tokenizer, prompt=prompt, verbose=True) ```
cpayne1303/cp2024-instruct	cpayne1303	"2024-11-28T13:02:39Z"	156	1	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "en", "dataset:teknium/OpenHermes-2.5", "base_model:cpayne1303/cp2024", "base_model:finetune:cpayne1303/cp2024", "license:apache-2.0", "model-index", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2024-11-27T19:22:31Z"	--- language: - en license: apache-2.0 library_name: transformers base_model: cpayne1303/cp2024 datasets: - teknium/OpenHermes-2.5 model-index: - name: cp2024-instruct results: - task: type: text-generation name: Text Generation dataset: name: IFEval (0-Shot) type: HuggingFaceH4/ifeval args: num_few_shot: 0 metrics: - type: inst_level_strict_acc and prompt_level_strict_acc value: 17.06 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cpayne1303/cp2024-instruct name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: BBH (3-Shot) type: BBH args: num_few_shot: 3 metrics: - type: acc_norm value: 2.48 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cpayne1303/cp2024-instruct name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MATH Lvl 5 (4-Shot) type: hendrycks/competition_math args: num_few_shot: 4 metrics: - type: exact_match value: 0.0 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cpayne1303/cp2024-instruct name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GPQA (0-shot) type: Idavidrein/gpqa args: num_few_shot: 0 metrics: - type: acc_norm value: 1.34 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cpayne1303/cp2024-instruct name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MuSR (0-shot) type: TAUR-Lab/MuSR args: num_few_shot: 0 metrics: - type: acc_norm value: 3.18 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cpayne1303/cp2024-instruct name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU-PRO (5-shot) type: TIGER-Lab/MMLU-Pro config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 1.85 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cpayne1303/cp2024-instruct name: Open LLM Leaderboard --- ## Model Description This is a model using the llama2 architecture and only 30 million parameters. It is based off of <a href = "https://huggingface.co/cpayne1303/cp2024">this model</a> and was finetuned on approximately 85 million tokens of instruct data from the first 20000 rows of the openhermes 2.5 dataset with a low learning rate of 2e-6 and context length of 512. # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_cpayne1303__cp2024-instruct) \| Metric \|Value\| \|-------------------\|----:\| \|Avg. \| 4.32\| \|IFEval (0-Shot) \|17.06\| \|BBH (3-Shot) \| 2.48\| \|MATH Lvl 5 (4-Shot)\| 0.00\| \|GPQA (0-shot) \| 1.34\| \|MuSR (0-shot) \| 3.18\| \|MMLU-PRO (5-shot) \| 1.85\|
Chenchuhui/Icelandic-finetuned-no-data-augmentation	Chenchuhui	"2023-12-18T17:43:02Z"	6	0	transformers	[ "transformers", "tensorboard", "safetensors", "wav2vec2", "automatic-speech-recognition", "generated_from_trainer", "base_model:carlosdanielhernandezmena/wav2vec2-large-xlsr-53-icelandic-ep10-1000h", "base_model:finetune:carlosdanielhernandezmena/wav2vec2-large-xlsr-53-icelandic-ep10-1000h", "license:cc-by-4.0", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	"2023-12-14T17:56:05Z"	--- license: cc-by-4.0 base_model: carlosdanielhernandezmena/wav2vec2-large-xlsr-53-icelandic-ep10-1000h tags: - generated_from_trainer metrics: - wer model-index: - name: Icelandic-finetuned-no-data-augmentation results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # Icelandic-finetuned-no-data-augmentation This model is a fine-tuned version of [carlosdanielhernandezmena/wav2vec2-large-xlsr-53-icelandic-ep10-1000h](https://huggingface.co/carlosdanielhernandezmena/wav2vec2-large-xlsr-53-icelandic-ep10-1000h) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.1262 - Wer: 0.1544 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0003 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 16 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 10 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Wer \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:------:\| \| No log \| 0.2 \| 10 \| 0.2849 \| 0.1667 \| \| No log \| 0.4 \| 20 \| 0.3085 \| 0.1611 \| \| No log \| 0.6 \| 30 \| 0.3264 \| 0.1600 \| \| No log \| 0.8 \| 40 \| 0.3149 \| 0.1577 \| \| 0.3456 \| 1.0 \| 50 \| 0.3221 \| 0.1588 \| \| 0.3456 \| 1.2 \| 60 \| 0.3183 \| 0.1577 \| \| 0.3456 \| 1.4 \| 70 \| 0.3133 \| 0.1510 \| \| 0.3456 \| 1.6 \| 80 \| 0.3069 \| 0.1521 \| \| 0.3456 \| 1.8 \| 90 \| 0.2970 \| 0.1521 \| \| 0.2689 \| 2.0 \| 100 \| 0.2782 \| 0.1477 \| \| 0.2689 \| 2.2 \| 110 \| 0.2242 \| 0.1488 \| \| 0.2689 \| 2.4 \| 120 \| 0.2257 \| 0.1454 \| \| 0.2689 \| 2.6 \| 130 \| 0.2722 \| 0.1521 \| \| 0.2689 \| 2.8 \| 140 \| 0.2564 \| 0.1488 \| \| 0.2312 \| 3.0 \| 150 \| 0.1811 \| 0.1521 \| \| 0.2312 \| 3.2 \| 160 \| 0.1762 \| 0.1454 \| \| 0.2312 \| 3.4 \| 170 \| 0.2154 \| 0.1421 \| \| 0.2312 \| 3.6 \| 180 \| 0.1873 \| 0.1465 \| \| 0.2312 \| 3.8 \| 190 \| 0.2015 \| 0.1465 \| \| 0.2153 \| 4.0 \| 200 \| 0.2402 \| 0.1499 \| \| 0.2153 \| 4.2 \| 210 \| 0.2366 \| 0.1454 \| \| 0.2153 \| 4.4 \| 220 \| 0.1890 \| 0.1477 \| \| 0.2153 \| 4.6 \| 230 \| 0.1897 \| 0.1499 \| \| 0.2153 \| 4.8 \| 240 \| 0.1777 \| 0.1488 \| \| 0.1986 \| 5.0 \| 250 \| 0.1659 \| 0.1555 \| \| 0.1986 \| 5.2 \| 260 \| 0.1936 \| 0.1588 \| \| 0.1986 \| 5.4 \| 270 \| 0.2044 \| 0.1532 \| \| 0.1986 \| 5.6 \| 280 \| 0.1958 \| 0.1555 \| \| 0.1986 \| 5.8 \| 290 \| 0.1760 \| 0.1521 \| \| 0.1842 \| 6.0 \| 300 \| 0.2056 \| 0.1600 \| \| 0.1842 \| 6.2 \| 310 \| 0.1649 \| 0.1532 \| \| 0.1842 \| 6.4 \| 320 \| 0.2269 \| 0.1532 \| \| 0.1842 \| 6.6 \| 330 \| 0.1572 \| 0.1488 \| \| 0.1842 \| 6.8 \| 340 \| 0.1890 \| 0.1600 \| \| 0.181 \| 7.0 \| 350 \| 0.1757 \| 0.1700 \| \| 0.181 \| 7.2 \| 360 \| 0.2322 \| 0.1644 \| \| 0.181 \| 7.4 \| 370 \| 0.2644 \| 0.1600 \| \| 0.181 \| 7.6 \| 380 \| 0.2047 \| 0.1555 \| \| 0.181 \| 7.8 \| 390 \| 0.2406 \| 0.1678 \| \| 0.1751 \| 8.0 \| 400 \| 0.2820 \| 0.1678 \| \| 0.1751 \| 8.2 \| 410 \| 0.2965 \| 0.1655 \| \| 0.1751 \| 8.4 \| 420 \| 0.2841 \| 0.1667 \| \| 0.1751 \| 8.6 \| 430 \| 0.2527 \| 0.1734 \| \| 0.1751 \| 8.8 \| 440 \| 0.5464 \| 0.1700 \| \| 0.1836 \| 9.0 \| 450 \| 0.2185 \| 0.1622 \| \| 0.1836 \| 9.2 \| 460 \| 0.2129 \| 0.1857 \| \| 0.1836 \| 9.4 \| 470 \| 0.3367 \| 0.1779 \| \| 0.1836 \| 9.6 \| 480 \| 0.1457 \| 0.1644 \| \| 0.1836 \| 9.8 \| 490 \| 0.1320 \| 0.1667 \| \| 0.2141 \| 10.0 \| 500 \| 0.1262 \| 0.1544 \| ### Framework versions - Transformers 4.35.2 - Pytorch 2.1.0+cu121 - Datasets 2.15.0 - Tokenizers 0.15.0
hahaqwqw/q-FrozenLake-v1-4x4-noSlippery	hahaqwqw	"2025-03-21T00:36:06Z"	0	0	null	[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	reinforcement-learning	"2025-03-21T00:36:03Z"	--- tags: - FrozenLake-v1-4x4-no_slippery - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-FrozenLake-v1-4x4-noSlippery results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: FrozenLake-v1-4x4-no_slippery type: FrozenLake-v1-4x4-no_slippery metrics: - type: mean_reward value: 1.00 +/- 0.00 name: mean_reward verified: false --- # Q-Learning Agent playing1 FrozenLake-v1 This is a trained model of a Q-Learning agent playing FrozenLake-v1 . ## Usage ```python model = load_from_hub(repo_id="hahaqwqw/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```
matatonic/Mistral-Small-24B-Instruct-2501-5.0bpw-exl2	matatonic	"2025-01-30T19:54:23Z"	21	0	vllm	[ "vllm", "safetensors", "mistral", "text-generation", "transformers", "conversational", "en", "fr", "de", "es", "it", "pt", "zh", "ja", "ru", "ko", "base_model:mistralai/Mistral-Small-24B-Base-2501", "base_model:quantized:mistralai/Mistral-Small-24B-Base-2501", "license:apache-2.0", "text-generation-inference", "5-bit", "exl2", "region:us" ]	text-generation	"2025-01-30T19:53:13Z"	--- language: - en - fr - de - es - it - pt - zh - ja - ru - ko license: apache-2.0 library_name: vllm inference: false base_model: - mistralai/Mistral-Small-24B-Base-2501 extra_gated_description: If you want to learn more about how we process your personal data, please read our <a href="https://mistral.ai/terms/">Privacy Policy</a>. tags: - transformers --- # Model Card for Mistral-Small-24B-Instruct-2501 Mistral Small 3 ( 2501 ) sets a new benchmark in the "small" Large Language Models category below 70B, boasting 24B parameters and achieving state-of-the-art capabilities comparable to larger models! This model is an instruction-fine-tuned version of the base model: [Mistral-Small-24B-Base-2501](https://huggingface.co/mistralai/Mistral-Small-24B-Base-2501). Mistral Small can be deployed locally and is exceptionally "knowledge-dense", fitting in a single RTX 4090 or a 32GB RAM MacBook once quantized. Perfect for: - Fast response conversational agents. - Low latency function calling. - Subject matter experts via fine-tuning. - Local inference for hobbyists and organizations handling sensitive data. For enterprises that need specialized capabilities (increased context, particular modalities, domain specific knowledge, etc.), we will be releasing commercial models beyond what Mistral AI contributes to the community. This release demonstrates our commitment to open source, serving as a strong base model. Learn more about Mistral Small in our [blog post](https://mistral.ai/news/mistral-small-3/). Model developper: Mistral AI Team ## Key Features - Multilingual: Supports dozens of languages, including English, French, German, Spanish, Italian, Chinese, Japanese, Korean, Portuguese, Dutch, and Polish. - Agent-Centric: Offers best-in-class agentic capabilities with native function calling and JSON outputting. - Advanced Reasoning: State-of-the-art conversational and reasoning capabilities. - Apache 2.0 License: Open license allowing usage and modification for both commercial and non-commercial purposes. - Context Window: A 32k context window. - System Prompt: Maintains strong adherence and support for system prompts. - Tokenizer: Utilizes a Tekken tokenizer with a 131k vocabulary size. ## Benchmark results ### Human evaluated benchmarks \| Category \| Gemma-2-27B \| Qwen-2.5-32B \| Llama-3.3-70B \| Gpt4o-mini \| \|----------\|-------------\|--------------\|---------------\|------------\| \| Mistral is better \| 0.536 \| 0.496 \| 0.192 \| 0.200 \| \| Mistral is slightly better \| 0.196 \| 0.184 \| 0.164 \| 0.204 \| \| Ties \| 0.052 \| 0.060 \| 0.236 \| 0.160 \| \| Other is slightly better \| 0.060 \| 0.088 \| 0.112 \| 0.124 \| \| Other is better \| 0.156 \| 0.172 \| 0.296 \| 0.312 \| Note: - We conducted side by side evaluations with an external third-party vendor, on a set of over 1k proprietary coding and generalist prompts. - Evaluators were tasked with selecting their preferred model response from anonymized generations produced by Mistral Small 3 vs another model. - We are aware that in some cases the benchmarks on human judgement starkly differ from publicly available benchmarks, but have taken extra caution in verifying a fair evaluation. We are confident that the above benchmarks are valid. ### Publicly accesible benchmarks Reasoning & Knowledge \| Evaluation \| mistral-small-24B-instruct-2501 \| gemma-2b-27b \| llama-3.3-70b \| qwen2.5-32b \| gpt-4o-mini-2024-07-18 \| \|------------\|---------------\|--------------\|---------------\|---------------\|-------------\| \| mmlu_pro_5shot_cot_instruct \| 0.663 \| 0.536 \| 0.666 \| 0.683 \| 0.617 \| \| gpqa_main_cot_5shot_instruct \| 0.453 \| 0.344 \| 0.531 \| 0.404 \| 0.377 \| Math & Coding \| Evaluation \| mistral-small-24B-instruct-2501 \| gemma-2b-27b \| llama-3.3-70b \| qwen2.5-32b \| gpt-4o-mini-2024-07-18 \| \|------------\|---------------\|--------------\|---------------\|---------------\|-------------\| \| humaneval_instruct_pass@1 \| 0.848 \| 0.732 \| 0.854 \| 0.909 \| 0.890 \| \| math_instruct \| 0.706 \| 0.535 \| 0.743 \| 0.819 \| 0.761 \| Instruction following \| Evaluation \| mistral-small-24B-instruct-2501 \| gemma-2b-27b \| llama-3.3-70b \| qwen2.5-32b \| gpt-4o-mini-2024-07-18 \| \|------------\|---------------\|--------------\|---------------\|---------------\|-------------\| \| mtbench_dev \| 8.35 \| 7.86 \| 7.96 \| 8.26 \| 8.33 \| \| wildbench \| 52.27 \| 48.21 \| 50.04 \| 52.73 \| 56.13 \| \| arena_hard \| 0.873 \| 0.788 \| 0.840 \| 0.860 \| 0.897 \| \| ifeval \| 0.829 \| 0.8065 \| 0.8835 \| 0.8401 \| 0.8499 \| Note: - Performance accuracy on all benchmarks were obtained through the same internal evaluation pipeline - as such, numbers may vary slightly from previously reported performance ([Qwen2.5-32B-Instruct](https://qwenlm.github.io/blog/qwen2.5/), [Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct), [Gemma-2-27B-IT](https://huggingface.co/google/gemma-2-27b-it)). - Judge based evals such as Wildbench, Arena hard and MTBench were based on gpt-4o-2024-05-13. ### Basic Instruct Template (V7-Tekken) ``` <s>[SYSTEM_PROMPT]<system prompt>[/SYSTEM_PROMPT][INST]<user message>[/INST]<assistant response></s>[INST]<user message>[/INST] ``` `<system_prompt>`, `<user message>` and `<assistant response>` are placeholders. *Please make sure to use [mistral-common](https://github.com/mistralai/mistral-common) as the source of truth* ## Usage The model can be used with the following frameworks; - [`vllm`](https://github.com/vllm-project/vllm): See [here](#vLLM) - [`transformers`](https://github.com/huggingface/transformers): See [here](#Transformers) ### vLLM We recommend using this model with the [vLLM library](https://github.com/vllm-project/vllm) to implement production-ready inference pipelines. Note 1: We recommond using a relatively low temperature, such as `temperature=0.15`. Note 2: Make sure to add a system prompt to the model to best tailer it for your needs. If you want to use the model as a general assistant, we recommend the following system prompt: ``` system_prompt = """You are Mistral Small 3, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris. Your knowledge base was last updated on 2023-10-01. The current date is 2025-01-30. When you're not sure about some information, you say that you don't have the information and don't make up anything. If the user's question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. \"What are some good restaurants around me?\" => \"Where are you?\" or \"When is the next flight to Tokyo\" => \"Where do you travel from?\")""" ``` _Installation_ Make sure you install [`vLLM >= 0.6.4`](https://github.com/vllm-project/vllm/releases/tag/v0.6.4): ``` pip install --upgrade vllm ``` Also make sure you have [`mistral_common >= 1.5.2`](https://github.com/mistralai/mistral-common/releases/tag/v1.5.2) installed: ``` pip install --upgrade mistral_common ``` You can also make use of a ready-to-go [docker image](https://github.com/vllm-project/vllm/blob/main/Dockerfile) or on the [docker hub](https://hub.docker.com/layers/vllm/vllm-openai/latest/images/sha256-de9032a92ffea7b5c007dad80b38fd44aac11eddc31c435f8e52f3b7404bbf39). #### Server We recommand that you use Mistral-Small-24B-Instruct-2501 in a server/client setting. 1. Spin up a server: ``` vllm serve mistralai/Mistral-Small-24B-Instruct-2501 --tokenizer_mode mistral --config_format mistral --load_format mistral --tool-call-parser mistral --enable-auto-tool-choice ``` Note: Running Mistral-Small-24B-Instruct-2501 on GPU requires ~55 GB of GPU RAM in bf16 or fp16. 2. To ping the client you can use a simple Python snippet. ```py import requests import json from datetime import datetime, timedelta url = "http://<your-server>:8000/v1/chat/completions" headers = {"Content-Type": "application/json", "Authorization": "Bearer token"} model = "mistralai/Mistral-Small-24B-Instruct-2501" messages = [ { "role": "system", "content": "You are a conversational agent that always answers straight to the point, always end your accurate response with an ASCII drawing of a cat." }, { "role": "user", "content": "Give me 5 non-formal ways to say 'See you later' in French." }, ] data = {"model": model, "messages": messages} response = requests.post(url, headers=headers, data=json.dumps(data)) print(response.json()["choices"][0]["message"]["content"]) # Sure, here are five non-formal ways to say "See you later" in French: # # 1. À plus tard # 2. À plus # 3. Salut # 4. À toute # 5. Bisous # # ``` # /\_/\ # ( o.o ) # > ^ < # ``` ``` ### Function calling Mistral-Small-24-Instruct-2501 is excellent at function / tool calling tasks via vLLM. E.g.: <details> <summary>Example</summary> ```py import requests import json from huggingface_hub import hf_hub_download from datetime import datetime, timedelta url = "http://<your-url>:8000/v1/chat/completions" headers = {"Content-Type": "application/json", "Authorization": "Bearer token"} model = "mistralai/Mistral-Small-24B-Instruct-2501" def load_system_prompt(repo_id: str, filename: str) -> str: file_path = hf_hub_download(repo_id=repo_id, filename=filename) with open(file_path, "r") as file: system_prompt = file.read() today = datetime.today().strftime("%Y-%m-%d") yesterday = (datetime.today() - timedelta(days=1)).strftime("%Y-%m-%d") model_name = repo_id.split("/")[-1] return system_prompt.format(name=model_name, today=today, yesterday=yesterday) SYSTEM_PROMPT = load_system_prompt(model, "SYSTEM_PROMPT.txt") tools = [ { "type": "function", "function": { "name": "get_current_weather", "description": "Get the current weather in a given location", "parameters": { "type": "object", "properties": { "city": { "type": "string", "description": "The city to find the weather for, e.g. 'San Francisco'", }, "state": { "type": "string", "description": "The state abbreviation, e.g. 'CA' for California", }, "unit": { "type": "string", "description": "The unit for temperature", "enum": ["celsius", "fahrenheit"], }, }, "required": ["city", "state", "unit"], }, }, }, { "type": "function", "function": { "name": "rewrite", "description": "Rewrite a given text for improved clarity", "parameters": { "type": "object", "properties": { "text": { "type": "string", "description": "The input text to rewrite", } }, }, }, }, ] messages = [ {"role": "system", "content": SYSTEM_PROMPT}, { "role": "user", "content": "Could you please make the below article more concise?\n\nOpenAI is an artificial intelligence research laboratory consisting of the non-profit OpenAI Incorporated and its for-profit subsidiary corporation OpenAI Limited Partnership.", }, { "role": "assistant", "content": "", "tool_calls": [ { "id": "bbc5b7ede", "type": "function", "function": { "name": "rewrite", "arguments": '{"text": "OpenAI is an artificial intelligence research laboratory consisting of the non-profit OpenAI Incorporated and its for-profit subsidiary corporation OpenAI Limited Partnership."}', }, } ], }, { "role": "tool", "content": '{"action":"rewrite","outcome":"OpenAI is a FOR-profit company."}', "tool_call_id": "bbc5b7ede", "name": "rewrite", }, { "role": "assistant", "content": "---\n\nOpenAI is a FOR-profit company.", }, { "role": "user", "content": "Can you tell me what the temperature will be in Dallas, in Fahrenheit?", }, ] data = {"model": model, "messages": messages, "tools": tools} response = requests.post(url, headers=headers, data=json.dumps(data)) import ipdb; ipdb.set_trace() print(response.json()["choices"][0]["message"]["tool_calls"]) # [{'id': '8PdihwL6d', 'type': 'function', 'function': {'name': 'get_current_weather', 'arguments': '{"city": "Dallas", "state": "TX", "unit": "fahrenheit"}'}}] ``` </details> #### Offline ```py from vllm import LLM from vllm.sampling_params import SamplingParams from datetime import datetime, timedelta SYSTEM_PROMPT = "You are a conversational agent that always answers straight to the point, always end your accurate response with an ASCII drawing of a cat." user_prompt = "Give me 5 non-formal ways to say 'See you later' in French." messages = [ { "role": "system", "content": SYSTEM_PROMPT }, { "role": "user", "content": user_prompt }, ] # note that running this model on GPU requires over 60 GB of GPU RAM llm = LLM(model=model_name, tokenizer_mode="mistral", tensor_parallel_size=8) sampling_params = SamplingParams(max_tokens=512, temperature=0.15) outputs = llm.chat(messages, sampling_params=sampling_params) print(outputs[0].outputs[0].text) # Sure, here are five non-formal ways to say "See you later" in French: # # 1. À plus tard # 2. À plus # 3. Salut # 4. À toute # 5. Bisous # # ``` # /\_/\ # ( o.o ) # > ^ < # ``` ``` ### Transformers If you want to use Hugging Face transformers to generate text, you can do something like this. ```py from transformers import pipeline import torch messages = [ {"role": "user", "content": "Give me 5 non-formal ways to say 'See you later' in French."}, ] chatbot = pipeline("text-generation", model="mistralai/Mistral-Small-24B-Instruct-2501", max_new_tokens=256, torch_dtype=torch.bfloat16) chatbot(messages) ``` ### Ollama [Ollama](https://github.com/ollama/ollama) can run this model locally on MacOS, Windows and Linux. ``` ollama run mistral-small ``` 4-bit quantization (aliased to default): ``` ollama run mistral-small:24b-instruct-2501-q4_K_M ``` 8-bit quantization: ``` ollama run mistral-small:24b-instruct-2501-q8_0 ``` FP16: ``` ollama run mistral-small:24b-instruct-2501-fp16 ```
aletorregrosab/caldeiro	aletorregrosab	"2025-01-15T17:56:03Z"	14	1	diffusers	[ "diffusers", "flux", "lora", "replicate", "text-to-image", "en", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "license:other", "region:us" ]	text-to-image	"2025-01-15T17:18:24Z"	--- license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md language: - en tags: - flux - diffusers - lora - replicate base_model: "black-forest-labs/FLUX.1-dev" pipeline_tag: text-to-image # widget: # - text: >- # prompt # output: # url: https://... instance_prompt: TOK --- # Caldeiro <Gallery /> Trained on Replicate using: https://replicate.com/ostris/flux-dev-lora-trainer/train ## Trigger words You should use `TOK` to trigger the image generation. ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers) ```py from diffusers import AutoPipelineForText2Image import torch pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda') pipeline.load_lora_weights('aletorregrosab/caldeiro', weight_name='lora.safetensors') image = pipeline('your prompt').images[0] ``` For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
hongngo/d9b7e1e9-09ca-44b5-8e0e-c662ed443109	hongngo	"2025-01-28T14:16:04Z"	6	0	peft	[ "peft", "safetensors", "llama", "axolotl", "generated_from_trainer", "base_model:01-ai/Yi-1.5-9B-Chat-16K", "base_model:adapter:01-ai/Yi-1.5-9B-Chat-16K", "license:apache-2.0", "8-bit", "bitsandbytes", "region:us" ]	null	"2025-01-28T12:27:10Z"	--- library_name: peft license: apache-2.0 base_model: 01-ai/Yi-1.5-9B-Chat-16K tags: - axolotl - generated_from_trainer model-index: - name: d9b7e1e9-09ca-44b5-8e0e-c662ed443109 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.4.1` ```yaml adapter: lora base_model: 01-ai/Yi-1.5-9B-Chat-16K bf16: auto chat_template: llama3 dataset_prepared_path: null datasets: - data_files: - 7a291b1d31d37167_train_data.json ds_type: json format: custom path: /workspace/input_data/7a291b1d31d37167_train_data.json type: field_instruction: instruction field_output: response format: '{instruction}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 128 eval_table_size: null evals_per_epoch: 1 flash_attention: true fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 4 gradient_checkpointing: true gradient_clipping: 1.0 group_by_length: false hub_model_id: hongngo/d9b7e1e9-09ca-44b5-8e0e-c662ed443109 hub_repo: null hub_strategy: end hub_token: null learning_rate: 5.0e-05 load_in_4bit: true load_in_8bit: true local_rank: null logging_steps: 1 lora_alpha: 16 lora_dropout: 0.05 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 8 lora_target_linear: true lr_scheduler: cosine max_steps: 200 micro_batch_size: 2 mlflow_experiment_name: /tmp/7a291b1d31d37167_train_data.json model_type: AutoModelForCausalLM num_epochs: 1 optimizer: adamw_bnb_8bit output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false saves_per_epoch: 1 sequence_len: 1024 strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: 57452f82-4de3-4f56-93da-17c43b36a921 wandb_project: Gradients-On-Demand wandb_run: your_name wandb_runid: 57452f82-4de3-4f56-93da-17c43b36a921 warmup_steps: 5 weight_decay: 0.01 xformers_attention: true ``` </details><br> # d9b7e1e9-09ca-44b5-8e0e-c662ed443109 This model is a fine-tuned version of [01-ai/Yi-1.5-9B-Chat-16K](https://huggingface.co/01-ai/Yi-1.5-9B-Chat-16K) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.3635 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 5 - training_steps: 200 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 0.1691 \| 0.0056 \| 200 \| 0.3635 \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
stablediffusionapi/deliberatev5-inpaintingsa	stablediffusionapi	"2024-03-25T14:48:12Z"	44	0	diffusers	[ "diffusers", "modelslab.com", "stable-diffusion-api", "text-to-image", "ultra-realistic", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	"2024-03-25T14:46:09Z"	--- license: creativeml-openrail-m tags: - modelslab.com - stable-diffusion-api - text-to-image - ultra-realistic pinned: true --- # Deliberate_v5-inpainting.safetensors API Inference ![generated from modelslab.com](https://pub-3626123a908346a7a8be8d9295f44e26.r2.dev/generations/17348316751711377913.png) ## Get API Key Get API key from [ModelsLab API](http://modelslab.com), No Payment needed. Replace Key in below code, change model_id to "deliberatev5-inpaintingsa" Coding in PHP/Node/Java etc? Have a look at docs for more code examples: [View docs](https://modelslab.com/docs) Try model for free: [Generate Images](https://modelslab.com/models/deliberatev5-inpaintingsa) Model link: [View model](https://modelslab.com/models/deliberatev5-inpaintingsa) View all models: [View Models](https://modelslab.com/models) import requests import json url = "https://modelslab.com/api/v6/images/text2img" payload = json.dumps({ "key": "your_api_key", "model_id": "deliberatev5-inpaintingsa", "prompt": "ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K", "negative_prompt": "painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime", "width": "512", "height": "512", "samples": "1", "num_inference_steps": "30", "safety_checker": "no", "enhance_prompt": "yes", "seed": None, "guidance_scale": 7.5, "multi_lingual": "no", "panorama": "no", "self_attention": "no", "upscale": "no", "embeddings": "embeddings_model_id", "lora": "lora_model_id", "webhook": None, "track_id": None }) headers = { 'Content-Type': 'application/json' } response = requests.request("POST", url, headers=headers, data=payload) print(response.text) > Use this coupon code to get 25% off DMGG0RBN
pjox/camembert-classical-fr-ner	pjox	"2023-01-18T14:15:25Z"	0	0	flair	[ "flair", "Early Modern French", "Historical", "NER", "token-classification", "fr", "dataset:freemner", "license:apache-2.0", "region:us" ]	token-classification	"2023-01-18T14:11:44Z"	--- language: fr tags: - Early Modern French - Historical - NER - flair license: apache-2.0 datasets: - freemner library_name: flair pipeline_tag: token-classification --- <a href="https://portizs.eu/publication/2022/lrec/dalembert/"> <img width="300px" src="https://portizs.eu/publication/2020/acl/camembert/featured_huac8a9374dbd7d6a2cb77224540858ab4_463389_720x2500_fit_q100_h2_lanczos_3.webp"> </a> # CamemBERT Early Modern French NER model This model is fine-tuned version of a [CamemBERT model](https://huggingface.co/camembert-base) on the [FreEMNER corpus](https://doi.org/10.5281/zenodo.6481135) for Early Modern French. It was introduced in [this paper](https://aclanthology.org/2022.coling-1.327/). ### BibTeX entry and citation info ```bibtex @inproceedings{ortiz-suarez-gabay-2022-data, title = "A Data-driven Approach to Named Entity Recognition for Early {M}odern {F}rench", author = "Ortiz Suarez, Pedro and Gabay, Simon", booktitle = "Proceedings of the 29th International Conference on Computational Linguistics", month = oct, year = "2022", address = "Gyeongju, Republic of Korea", publisher = "International Committee on Computational Linguistics", url = "https://aclanthology.org/2022.coling-1.327", pages = "3722--3730", abstract = "Named entity recognition has become an increasingly useful tool for digital humanities research, specially when it comes to historical texts. However, historical texts pose a wide range of challenges to both named entity recognition and natural language processing in general that are still difficult to address even with modern neural methods. In this article we focus in named entity recognition for historical French, and in particular for Early Modern French (16th-18th c.), i.e. Ancien R{\'e}gime French. However, instead of developing a specialised architecture to tackle the particularities of this state of language, we opt for a data-driven approach by developing a new corpus with fine-grained entity annotation, covering three centuries of literature corresponding to the early modern period; we try to annotate as much data as possible producing a corpus that is many times bigger than the most popular NER evaluation corpora for both Contemporary English and French. We then fine-tune existing state-of-the-art architectures for Early Modern and Contemporary French, obtaining results that are on par with those of the current state-of-the-art NER systems for Contemporary English. Both the corpus and the fine-tuned models are released.", } ```
microsoft/unispeech-1350-en-353-fr-ft-1h	microsoft	"2021-12-19T23:14:27Z"	47	0	transformers	[ "transformers", "pytorch", "unispeech", "automatic-speech-recognition", "audio", "fr", "dataset:common_voice", "arxiv:2101.07597", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	"2022-03-02T23:29:05Z"	--- language: - fr datasets: - common_voice tags: - audio - automatic-speech-recognition --- # UniSpeech-Large-plus FRENCH [Microsoft's UniSpeech](https://www.microsoft.com/en-us/research/publication/unispeech-unified-speech-representation-learning-with-labeled-and-unlabeled-data/) The large model pretrained on 16kHz sampled speech audio and phonetic labels and consequently fine-tuned on 1h of French phonemes. When using the model make sure that your speech input is also sampled at 16kHz and your text in converted into a sequence of phonemes. [Paper: UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data](https://arxiv.org/abs/2101.07597) Authors: Chengyi Wang, Yu Wu, Yao Qian, Kenichi Kumatani, Shujie Liu, Furu Wei, Michael Zeng, Xuedong Huang Abstract In this paper, we propose a unified pre-training approach called UniSpeech to learn speech representations with both unlabeled and labeled data, in which supervised phonetic CTC learning and phonetically-aware contrastive self-supervised learning are conducted in a multi-task learning manner. The resultant representations can capture information more correlated with phonetic structures and improve the generalization across languages and domains. We evaluate the effectiveness of UniSpeech for cross-lingual representation learning on public CommonVoice corpus. The results show that UniSpeech outperforms self-supervised pretraining and supervised transfer learning for speech recognition by a maximum of 13.4% and 17.8% relative phone error rate reductions respectively (averaged over all testing languages). The transferability of UniSpeech is also demonstrated on a domain-shift speech recognition task, i.e., a relative word error rate reduction of 6% against the previous approach. The original model can be found under https://github.com/microsoft/UniSpeech/tree/main/UniSpeech. # Usage This is an speech model that has been fine-tuned on phoneme classification. ## Inference ```python import torch from datasets import load_dataset from transformers import AutoModelForCTC, AutoProcessor import torchaudio.functional as F model_id = "microsoft/unispeech-1350-en-353-fr-ft-1h" sample = next(iter(load_dataset("common_voice", "fr", split="test", streaming=True))) resampled_audio = F.resample(torch.tensor(sample["audio"]["array"]), 48_000, 16_000).numpy() model = AutoModelForCTC.from_pretrained(model_id) processor = AutoProcessor.from_pretrained(model_id) input_values = processor(resampled_audio, return_tensors="pt").input_values with torch.no_grad(): logits = model(input_values).logits prediction_ids = torch.argmax(logits, dim=-1) transcription = processor.batch_decode(prediction_ids) # gives -> 'œ̃ v ʁ ɛ t ʁ a v a j ɛ̃ t e ʁ ɛ s ɑ̃ v a ɑ̃ f ɛ̃ ɛ t ʁ ə m ə n e s y ʁ s ə s y ʒ ɛ' # for 'Un vrai travail intéressant va, enfin, être mené sur ce sujet.' ``` # Contribution The model was contributed by [cywang](https://huggingface.co/cywang) and [patrickvonplaten](https://huggingface.co/patrickvonplaten). # License The official license can be found [here](https://github.com/microsoft/UniSpeech/blob/main/LICENSE) # Official Results See UniSpeeech-L^{+} - fr: ![design](https://raw.githubusercontent.com/patrickvonplaten/scientific_images/master/unispeech_results.png)
JoBuettner/rl_course_vizdoom_health_gathering_supreme	JoBuettner	"2023-05-23T21:44:18Z"	0	0	sample-factory	[ "sample-factory", "tensorboard", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	"2023-05-23T21:20:00Z"	--- library_name: sample-factory tags: - deep-reinforcement-learning - reinforcement-learning - sample-factory model-index: - name: APPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: doom_health_gathering_supreme type: doom_health_gathering_supreme metrics: - type: mean_reward value: 12.73 +/- 5.75 name: mean_reward verified: false --- A(n) APPO model trained on the doom_health_gathering_supreme environment. This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory. Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/ ## Downloading the model After installing Sample-Factory, download the model with: ``` python -m sample_factory.huggingface.load_from_hub -r JoBuettner/rl_course_vizdoom_health_gathering_supreme ``` ## Using the model To run the model after download, use the `enjoy` script corresponding to this environment: ``` python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme ``` You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag. See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details ## Training with this model To continue training with this model, use the `train` script corresponding to this environment: ``` python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000 ``` Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
AIBreaker25/ai	AIBreaker25	"2025-02-13T08:27:07Z"	0	0	null	[ "license:apache-2.0", "region:us" ]	null	"2025-02-13T08:27:01Z"	--- license: apache-2.0 ---
sambanovasystems/SambaLingo-Thai-Chat	sambanovasystems	"2024-04-16T22:38:55Z"	197	37	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "th", "en", "dataset:HuggingFaceH4/ultrachat_200k", "dataset:HuggingFaceH4/ultrafeedback_binarized", "dataset:HuggingFaceH4/cai-conversation-harmless", "arxiv:2404.05829", "license:llama2", "model-index", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2024-02-15T22:46:41Z"	--- language: - th - en license: llama2 datasets: - HuggingFaceH4/ultrachat_200k - HuggingFaceH4/ultrafeedback_binarized - HuggingFaceH4/cai-conversation-harmless model-index: - name: SambaLingo-Thai-Chat results: - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm value: 52.73 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sambanovasystems/SambaLingo-Thai-Chat name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm value: 78.42 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sambanovasystems/SambaLingo-Thai-Chat name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc value: 43.95 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sambanovasystems/SambaLingo-Thai-Chat name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 40.84 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sambanovasystems/SambaLingo-Thai-Chat name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc value: 72.22 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sambanovasystems/SambaLingo-Thai-Chat name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 8.57 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sambanovasystems/SambaLingo-Thai-Chat name: Open LLM Leaderboard --- # SambaLingo-Thai-Chat <img src="SambaLingo_Logo.png" width="340" style="margin-left:'auto' margin-right:'auto' display:'block'"/> <!-- Provide a quick summary of what the model is/does. --> SambaLingo-Thai-Chat is a human aligned chat model trained in Thai and English. It is trained using direct preference optimization on top the base model [SambaLingo-Thai-Base](https://huggingface.co/sambanovasystems/SambaLingo-Thai-Base). The base model adapts [Llama-2-7b](https://huggingface.co/meta-llama/Llama-2-7b-hf) to Thai by training on 38 billion tokens from the Thai split of the [Cultura-X](https://huggingface.co/datasets/uonlp/CulturaX) dataset. Try This Model at [SambaLingo-chat-space](https://huggingface.co/spaces/sambanovasystems/SambaLingo-chat-space). ## Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: [SambaNova Systems](https://sambanova.ai/) - Model type: Language Model - Language(s): Thai, English - Finetuned from model: [Llama-2-7b](https://huggingface.co/meta-llama/Llama-2-7b-hf) - Try This Model: [SambaLingo-chat-space](https://huggingface.co/spaces/sambanovasystems/SambaLingo-chat-space) - Paper: [SambaLingo: Teaching Large Language Models New Languages](https://arxiv.org/abs/2404.05829) - Blog Post: [sambalingo-open-source-language-experts](https://sambanova.ai/blog/sambalingo-open-source-language-experts) ## Getting Started ### Loading Model With Hugging Face Please make sure to set use_fast=False when loading the tokenizer. ```python from transformers import AutoModelForCausalLM, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("sambanovasystems/SambaLingo-Thai-Chat", use_fast=False) model = AutoModelForCausalLM.from_pretrained("sambanovasystems/SambaLingo-Thai-Chat", device_map="auto", torch_dtype="auto") ``` ### Interacting With Model Pipeline Please make sure to set use_fast=False when loading the tokenizer. ```python from transformers import pipeline pipe = pipeline("text-generation", model="sambanovasystems/SambaLingo-Thai-Chat", device_map="auto", use_fast=False) messages = [ {"role": "user", "content": {YOUR_QUESTION}}, ] prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) outputs = pipe(prompt)[0] outputs = outputs["generated_text"] ``` ### Suggested Inference Parameters - Temperature: 0.8 - Repetition penalty: 1.0 - Top-p: 0.9 ### Prompting Guidelines To prompt this model, please use the following chat template: ``` <\|user\|>\n{question}</s>\n<\|assistant\|>\n ``` ### Example Prompts and Generations ``` <\|user\|> ปรัชญาทางเศรษฐกิจที่พระบาทสมเด็จพระมหาภูมิพลอดุลยเดชมหาราช บรมนาถบพิตรมีพระราชดำรัสแก่ชาวไทย มีชื่อว่าอะไร</s> <\|assistant\|> ปรัชญาทางเศรษฐกิจที่พระบาทสมเด็จพระปรมินทรมหาภูมิพลอดุลยเดชทรงมีพระราชดำรัสแก่ชาวไทยเรียกว่า "ปรัชญาเศรษฐกิจพอเพียง" ปรัชญานี้เน้นความสำคัญของการพัฒนาแบบองค์รวมแ ละความสมดุล โดยคำนึงถึงสภาพแวดล้อมทางสังคม เศรษฐกิจ และสิ่งแวดล้อม ปรัชญาเศรษฐกิจพอเพียงเน้นความสำคัญของการพึ่งพาตนเอง ความมีเหตุผล และการประหยัด ตลอดจนความสำคัญของก ารพัฒนาจิตใจและจิตวิญญาณ ปรัชญานี้เน้นย้ำถึงความสำคัญของการดำเนินชีวิตอย่างพอประมาณ มีเหตุผล และมีคุณธรรม ตลอดจนความสำคัญของการพัฒนาความรู้และทักษะอย่างต่อเนื่อง ปรัชญาเศรษฐกิ จพอเพียงได้รับการยกย่องอย่างกว้างขวางว่าเป็นแนวทางแก้ไขปัญหาการพัฒนาที่ยั่งยืนและเป็นแนวทางในการดำเนินชีวิตที่นำไปสู่ความสุขและความเป็นอยู่ที่ดี ``` ## Training Details The alignment phase follows the recipe for [Zephyr-7B](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta), and comprises two stages: supervised fine-tuning (SFT) and Direct Performance Optimization (DPO). The SFT phase was done on the [ultrachat_200k](https://huggingface.co/datasets/HuggingFaceH4/ultrachat_200k) dataset mixed with the Google translated version of the ultrachat_200k dataset. It was trained for one epoch with global batch size 512 and max sequence length 2048 tokens. We used a linear decay learning rate of 2e-5 and 10% warmup. The DPO phase was done on the [ultrafeedback](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized) dataset and [cai-conversation-harmless](https://huggingface.co/datasets/HuggingFaceH4/cai-conversation-harmless) dataset, mixed with 10% of the data Google translated. It was trained with global batch size 32 and for three epochs. We used a linear decay learning rate of 5e-7, 10% warmup and β=0.1 as the regularization factor for DPO. ## Tokenizer Details We extended the vocabulary of the base llama model from 32,000 tokens to 57,000 tokens by adding up to 25,000 non-overlapping tokens from the new language. ## Evaluation For evaluation results see our paper: [SambaLingo: Teaching Large Language Models New Languages](https://arxiv.org/abs/2404.05829) ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> Use of this model is governed by the Meta’s [Llama 2 Community License Agreement](https://ai.meta.com/llama/license/). Please review and accept the license before downloading the model weights. ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> SambaLingo should NOT be used for: - Mission-critical applications - Applications that involve the safety of others - Making highly important decisions ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> Like all LLMs, SambaLingo has certain limitations: - Hallucination: Model may sometimes generate responses that contain plausible-sounding but factually incorrect or irrelevant information. - Code Switching: The model might unintentionally switch between languages or dialects within a single response, affecting the coherence and understandability of the output. - Repetition: The Model may produce repetitive phrases or sentences, leading to less engaging and informative responses. - Coding and Math: The model's performance in generating accurate code or solving complex mathematical problems may be limited. - Toxicity: The model could inadvertently generate responses containing inappropriate or harmful content. ## Acknowledgments We extend our heartfelt gratitude to the open-source AI community; this endeavor would not have been possible without open source. SambaNova embraces the open-source community and aspires to actively contribute to this initiative. We would like to give a special thanks to the following groups: - Meta for open sourcing LLama 2 and open sourcing FLORES-200 dataset - Nguyen et al for open sourcing CulturaX dataset - CohereAI for releasing AYA-101 and open sourcing a multilingual instruction tuning dataset - EleutherAI for their open source evaluation framework - Hugging Face-H4 team for open source the zephyr training recipe and alignment handbook repo ## Cite SambaLingo ``` @misc{csaki2024sambalingo, title={SambaLingo: Teaching Large Language Models New Languages}, author={Zoltan Csaki and Bo Li and Jonathan Li and Qiantong Xu and Pian Pawakapan and Leon Zhang and Yun Du and Hengyu Zhao and Changran Hu and Urmish Thakker}, year={2024}, eprint={2404.05829}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_sambanovasystems__SambaLingo-Thai-Chat) \| Metric \|Value\| \|---------------------------------\|----:\| \|Avg. \|49.45\| \|AI2 Reasoning Challenge (25-Shot)\|52.73\| \|HellaSwag (10-Shot) \|78.42\| \|MMLU (5-Shot) \|43.95\| \|TruthfulQA (0-shot) \|40.84\| \|Winogrande (5-shot) \|72.22\| \|GSM8k (5-shot) \| 8.57\|
HamZurger/Taxi-V3	HamZurger	"2023-07-30T18:45:37Z"	0	0	null	[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	reinforcement-learning	"2023-07-30T18:45:36Z"	--- tags: - Taxi-v3 - q-learning - reinforcement-learning - custom-implementation model-index: - name: Taxi-V3 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Taxi-v3 type: Taxi-v3 metrics: - type: mean_reward value: 7.54 +/- 2.69 name: mean_reward verified: false --- # Q-Learning Agent playing1 Taxi-v3 This is a trained model of a Q-Learning agent playing Taxi-v3 . ## Usage ```python model = load_from_hub(repo_id="HamZurger/Taxi-V3", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```
mlc-ai/DeepSeek-R1-Distill-Llama-70B-q4f16_1-MLC	mlc-ai	"2025-01-21T08:03:05Z"	15	0	mlc-llm	[ "mlc-llm", "web-llm", "base_model:deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "base_model:quantized:deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "region:us" ]	null	"2025-01-21T02:19:24Z"	--- library_name: mlc-llm base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-70B tags: - mlc-llm - web-llm --- # DeepSeek-R1-Distill-Llama-70B-q4f16_1-MLC This is the [DeepSeek-R1-Distill-Llama-70B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B) model in MLC format `q4f16_1`. The model can be used for projects [MLC-LLM](https://github.com/mlc-ai/mlc-llm) and [WebLLM](https://github.com/mlc-ai/web-llm). ## Example Usage Here are some examples of using this model in MLC LLM. Before running the examples, please install MLC LLM by following the [installation documentation](https://llm.mlc.ai/docs/install/mlc_llm.html#install-mlc-packages). ### Chat In command line, run ```bash mlc_llm chat HF://mlc-ai/DeepSeek-R1-Distill-Llama-70B-q4f16_1-MLC ``` ### REST Server In command line, run ```bash mlc_llm serve HF://mlc-ai/DeepSeek-R1-Distill-Llama-70B-q4f16_1-MLC ``` ### Python API ```python from mlc_llm import MLCEngine # Create engine model = "HF://mlc-ai/DeepSeek-R1-Distill-Llama-70B-q4f16_1-MLC" engine = MLCEngine(model) # Run chat completion in OpenAI API. for response in engine.chat.completions.create( messages=[{"role": "user", "content": "What is the meaning of life?"}], model=model, stream=True, ): for choice in response.choices: print(choice.delta.content, end="", flush=True) print("\n") engine.terminate() ``` ## Documentation For more information on MLC LLM project, please visit our [documentation](https://llm.mlc.ai/docs/) and [GitHub repo](http://github.com/mlc-ai/mlc-llm).
YakovElm/Hyperledger5SetFitModel_balance_ratio_2	YakovElm	"2023-06-01T09:28:12Z"	3	0	sentence-transformers	[ "sentence-transformers", "pytorch", "mpnet", "setfit", "text-classification", "arxiv:2209.11055", "license:apache-2.0", "region:us" ]	text-classification	"2023-06-01T09:27:31Z"	--- license: apache-2.0 tags: - setfit - sentence-transformers - text-classification pipeline_tag: text-classification --- # YakovElm/Hyperledger5SetFitModel_balance_ratio_2 This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves: 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning. 2. Training a classification head with features from the fine-tuned Sentence Transformer. ## Usage To use this model for inference, first install the SetFit library: ```bash python -m pip install setfit ``` You can then run inference as follows: ```python from setfit import SetFitModel # Download from Hub and run inference model = SetFitModel.from_pretrained("YakovElm/Hyperledger5SetFitModel_balance_ratio_2") # Run inference preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"]) ``` ## BibTeX entry and citation info ```bibtex @article{https://doi.org/10.48550/arxiv.2209.11055, doi = {10.48550/ARXIV.2209.11055}, url = {https://arxiv.org/abs/2209.11055}, author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren}, keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences}, title = {Efficient Few-Shot Learning Without Prompts}, publisher = {arXiv}, year = {2022}, copyright = {Creative Commons Attribution 4.0 International} } ```
PhillipGuo/hp-lat-llama-genericized_diff_hp_indices-epsilon10.0-pgd_layer15-def_layer0-harmless-102	PhillipGuo	"2024-05-21T02:31:08Z"	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	"2024-05-21T02:31:05Z"	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
0x1202/65ff08e2-c60e-4c92-999a-e6285a3d2ad1	0x1202	"2025-01-14T03:19:03Z"	8	0	peft	[ "peft", "safetensors", "qwen2", "axolotl", "generated_from_trainer", "base_model:Qwen/Qwen2.5-1.5B", "base_model:adapter:Qwen/Qwen2.5-1.5B", "license:apache-2.0", "region:us" ]	null	"2025-01-14T02:23:17Z"	--- library_name: peft license: apache-2.0 base_model: Qwen/Qwen2.5-1.5B tags: - axolotl - generated_from_trainer model-index: - name: 65ff08e2-c60e-4c92-999a-e6285a3d2ad1 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.4.1` ```yaml adapter: lora base_model: Qwen/Qwen2.5-1.5B bf16: auto chat_template: llama3 dataset_prepared_path: null datasets: - data_files: - 2f22bb3438fdbdeb_train_data.json ds_type: json format: custom path: /workspace/input_data/2f22bb3438fdbdeb_train_data.json type: field_instruction: english field_output: korean format: '{instruction}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null device_map: auto do_eval: true early_stopping_patience: null eval_batch_size: 2 eval_max_new_tokens: 128 eval_steps: null eval_table_size: null evals_per_epoch: 4 flash_attention: true fp16: false fsdp: null fsdp_config: null gradient_accumulation_steps: 4 gradient_checkpointing: false group_by_length: true hub_model_id: 0x1202/65ff08e2-c60e-4c92-999a-e6285a3d2ad1 hub_repo: null hub_strategy: checkpoint hub_token: null learning_rate: 0.0001 load_in_4bit: false load_in_8bit: false local_rank: null logging_steps: 5 lora_alpha: 16 lora_dropout: 0.05 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 8 lora_target_linear: true lr_scheduler: cosine max_grad_norm: 1.0 max_memory: 0: 75GB max_steps: 400 micro_batch_size: 2 mlflow_experiment_name: /tmp/2f22bb3438fdbdeb_train_data.json model_type: AutoModelForCausalLM num_epochs: 1 optimizer: adamw_bnb_8bit output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false save_steps: null saves_per_epoch: null sequence_len: 1024 strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: be31c0da-9110-4803-817b-2f1d224c3c6a wandb_project: Gradients-On-Demand wandb_run: your_name wandb_runid: be31c0da-9110-4803-817b-2f1d224c3c6a warmup_steps: 30 weight_decay: 0.0 xformers_attention: null ``` </details><br> # 65ff08e2-c60e-4c92-999a-e6285a3d2ad1 This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.8997 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 30 - training_steps: 400 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| No log \| 0.0000 \| 1 \| 1.6306 \| \| 1.4292 \| 0.0027 \| 100 \| 1.0239 \| \| 1.6539 \| 0.0054 \| 200 \| 0.9393 \| \| 1.4139 \| 0.0081 \| 300 \| 0.9036 \| \| 1.2223 \| 0.0108 \| 400 \| 0.8997 \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
bartowski/WhiteRabbitNeo-7B-v1.5a-GGUF	bartowski	"2024-03-13T21:57:05Z"	269	3	null	[ "gguf", "text-generation", "license:other", "endpoints_compatible", "region:us" ]	text-generation	"2024-03-09T17:08:49Z"	--- license: other license_name: deepseek license_link: https://huggingface.co/deepseek-ai/deepseek-coder-33b-base/blob/main/LICENSE quantized_by: bartowski pipeline_tag: text-generation --- ## Llamacpp Quantizations of WhiteRabbitNeo-7B-v1.5a Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2354">b2354</a> for quantization. Original model: https://huggingface.co/WhiteRabbitNeo/WhiteRabbitNeo-7B-v1.5a Download a file (not the whole branch) from below: \| Filename \| Quant type \| File Size \| Description \| \| -------- \| ---------- \| --------- \| ----------- \| \| [WhiteRabbitNeo-7B-v1.5a-Q8_0.gguf](https://huggingface.co/bartowski/WhiteRabbitNeo-7B-v1.5a-GGUF/blob/main/WhiteRabbitNeo-7B-v1.5a-Q8_0.gguf) \| Q8_0 \| 7.16GB \| Extremely high quality, generally unneeded but max available quant. \| \| [WhiteRabbitNeo-7B-v1.5a-Q6_K.gguf](https://huggingface.co/bartowski/WhiteRabbitNeo-7B-v1.5a-GGUF/blob/main/WhiteRabbitNeo-7B-v1.5a-Q6_K.gguf) \| Q6_K \| 5.53GB \| Very high quality, near perfect, recommended. \| \| [WhiteRabbitNeo-7B-v1.5a-Q5_K_M.gguf](https://huggingface.co/bartowski/WhiteRabbitNeo-7B-v1.5a-GGUF/blob/main/WhiteRabbitNeo-7B-v1.5a-Q5_K_M.gguf) \| Q5_K_M \| 4.78GB \| High quality, very usable. \| \| [WhiteRabbitNeo-7B-v1.5a-Q5_K_S.gguf](https://huggingface.co/bartowski/WhiteRabbitNeo-7B-v1.5a-GGUF/blob/main/WhiteRabbitNeo-7B-v1.5a-Q5_K_S.gguf) \| Q5_K_S \| 4.65GB \| High quality, very usable. \| \| [WhiteRabbitNeo-7B-v1.5a-Q5_0.gguf](https://huggingface.co/bartowski/WhiteRabbitNeo-7B-v1.5a-GGUF/blob/main/WhiteRabbitNeo-7B-v1.5a-Q5_0.gguf) \| Q5_0 \| 4.65GB \| High quality, older format, generally not recommended. \| \| [WhiteRabbitNeo-7B-v1.5a-Q4_K_M.gguf](https://huggingface.co/bartowski/WhiteRabbitNeo-7B-v1.5a-GGUF/blob/main/WhiteRabbitNeo-7B-v1.5a-Q4_K_M.gguf) \| Q4_K_M \| 4.08GB \| Good quality, similar to 4.25 bpw. \| \| [WhiteRabbitNeo-7B-v1.5a-Q4_K_S.gguf](https://huggingface.co/bartowski/WhiteRabbitNeo-7B-v1.5a-GGUF/blob/main/WhiteRabbitNeo-7B-v1.5a-Q4_K_S.gguf) \| Q4_K_S \| 3.85GB \| Slightly lower quality with small space savings. \| \| [WhiteRabbitNeo-7B-v1.5a-Q4_0.gguf](https://huggingface.co/bartowski/WhiteRabbitNeo-7B-v1.5a-GGUF/blob/main/WhiteRabbitNeo-7B-v1.5a-Q4_0.gguf) \| Q4_0 \| 3.82GB \| Decent quality, older format, generally not recommended. \| \| [WhiteRabbitNeo-7B-v1.5a-Q3_K_L.gguf](https://huggingface.co/bartowski/WhiteRabbitNeo-7B-v1.5a-GGUF/blob/main/WhiteRabbitNeo-7B-v1.5a-Q3_K_L.gguf) \| Q3_K_L \| 3.59GB \| Lower quality but usable, good for low RAM availability. \| \| [WhiteRabbitNeo-7B-v1.5a-Q3_K_M.gguf](https://huggingface.co/bartowski/WhiteRabbitNeo-7B-v1.5a-GGUF/blob/main/WhiteRabbitNeo-7B-v1.5a-Q3_K_M.gguf) \| Q3_K_M \| 3.29GB \| Even lower quality. \| \| [WhiteRabbitNeo-7B-v1.5a-Q3_K_S.gguf](https://huggingface.co/bartowski/WhiteRabbitNeo-7B-v1.5a-GGUF/blobblob/main/WhiteRabbitNeo-7B-v1.5a-Q3_K_S.gguf) \| Q3_K_S \| 2.94GB \| Low quality, not recommended. \| \| [WhiteRabbitNeo-7B-v1.5a-Q2_K.gguf](https://huggingface.co/bartowski/WhiteRabbitNeo-7B-v1.5a-GGUF/blob/main/WhiteRabbitNeo-7B-v1.5a-Q2_K.gguf) \| Q2_K \| 2.53GB \| Extremely low quality, not recommended. Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
mradermacher/hermes-llama3-roleplay-2000-v3-i1-GGUF	mradermacher	"2025-02-03T06:45:30Z"	181	1	transformers	[ "transformers", "gguf", "en", "base_model:Deev124/hermes-llama3-roleplay-2000-v3", "base_model:quantized:Deev124/hermes-llama3-roleplay-2000-v3", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	null	"2024-11-21T16:09:18Z"	--- base_model: Deev124/hermes-llama3-roleplay-2000-v3 language: - en library_name: transformers quantized_by: mradermacher tags: [] --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/Deev124/hermes-llama3-roleplay-2000-v3 <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v3-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v3-i1-GGUF/resolve/main/hermes-llama3-roleplay-2000-v3.i1-IQ1_S.gguf) \| i1-IQ1_S \| 2.1 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v3-i1-GGUF/resolve/main/hermes-llama3-roleplay-2000-v3.i1-IQ1_M.gguf) \| i1-IQ1_M \| 2.3 \| mostly desperate \| \| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v3-i1-GGUF/resolve/main/hermes-llama3-roleplay-2000-v3.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 2.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v3-i1-GGUF/resolve/main/hermes-llama3-roleplay-2000-v3.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 2.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v3-i1-GGUF/resolve/main/hermes-llama3-roleplay-2000-v3.i1-IQ2_S.gguf) \| i1-IQ2_S \| 2.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v3-i1-GGUF/resolve/main/hermes-llama3-roleplay-2000-v3.i1-IQ2_M.gguf) \| i1-IQ2_M \| 3.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v3-i1-GGUF/resolve/main/hermes-llama3-roleplay-2000-v3.i1-Q2_K.gguf) \| i1-Q2_K \| 3.3 \| IQ3_XXS probably better \| \| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v3-i1-GGUF/resolve/main/hermes-llama3-roleplay-2000-v3.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 3.4 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v3-i1-GGUF/resolve/main/hermes-llama3-roleplay-2000-v3.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 3.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v3-i1-GGUF/resolve/main/hermes-llama3-roleplay-2000-v3.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 3.8 \| IQ3_XS probably better \| \| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v3-i1-GGUF/resolve/main/hermes-llama3-roleplay-2000-v3.i1-IQ3_S.gguf) \| i1-IQ3_S \| 3.8 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v3-i1-GGUF/resolve/main/hermes-llama3-roleplay-2000-v3.i1-IQ3_M.gguf) \| i1-IQ3_M \| 3.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v3-i1-GGUF/resolve/main/hermes-llama3-roleplay-2000-v3.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 4.1 \| IQ3_S probably better \| \| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v3-i1-GGUF/resolve/main/hermes-llama3-roleplay-2000-v3.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 4.4 \| IQ3_M probably better \| \| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v3-i1-GGUF/resolve/main/hermes-llama3-roleplay-2000-v3.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 4.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v3-i1-GGUF/resolve/main/hermes-llama3-roleplay-2000-v3.i1-Q4_0_4_4.gguf) \| i1-Q4_0_4_4 \| 4.8 \| fast on arm, low quality \| \| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v3-i1-GGUF/resolve/main/hermes-llama3-roleplay-2000-v3.i1-Q4_0_4_8.gguf) \| i1-Q4_0_4_8 \| 4.8 \| fast on arm+i8mm, low quality \| \| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v3-i1-GGUF/resolve/main/hermes-llama3-roleplay-2000-v3.i1-Q4_0_8_8.gguf) \| i1-Q4_0_8_8 \| 4.8 \| fast on arm+sve, low quality \| \| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v3-i1-GGUF/resolve/main/hermes-llama3-roleplay-2000-v3.i1-Q4_0.gguf) \| i1-Q4_0 \| 4.8 \| fast, low quality \| \| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v3-i1-GGUF/resolve/main/hermes-llama3-roleplay-2000-v3.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 4.8 \| optimal size/speed/quality \| \| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v3-i1-GGUF/resolve/main/hermes-llama3-roleplay-2000-v3.i1-Q4_K_M.gguf) \| i1-Q4_K_M \| 5.0 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v3-i1-GGUF/resolve/main/hermes-llama3-roleplay-2000-v3.i1-Q5_K_S.gguf) \| i1-Q5_K_S \| 5.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v3-i1-GGUF/resolve/main/hermes-llama3-roleplay-2000-v3.i1-Q5_K_M.gguf) \| i1-Q5_K_M \| 5.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/hermes-llama3-roleplay-2000-v3-i1-GGUF/resolve/main/hermes-llama3-roleplay-2000-v3.i1-Q6_K.gguf) \| i1-Q6_K \| 6.7 \| practically like static Q6_K \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. <!-- end -->
JordanTensor/gemma-sandbagging-ppvvz1jq-step1024	JordanTensor	"2025-02-20T15:30:09Z"	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	"2025-02-20T15:30:03Z"	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
claterza/dqn-SpaceInvadersNoFrameskip-v4	claterza	"2022-12-29T03:03:21Z"	2	0	stable-baselines3	[ "stable-baselines3", "SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	"2022-12-29T03:02:44Z"	--- library_name: stable-baselines3 tags: - SpaceInvadersNoFrameskip-v4 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: DQN results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: SpaceInvadersNoFrameskip-v4 type: SpaceInvadersNoFrameskip-v4 metrics: - type: mean_reward value: 606.50 +/- 131.09 name: mean_reward verified: false --- # DQN Agent playing SpaceInvadersNoFrameskip-v4 This is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3) and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo). The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included. ## Usage (with SB3 RL Zoo) RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/> SB3: https://github.com/DLR-RM/stable-baselines3<br/> SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib ``` # Download model and save it into the logs/ folder python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga claterza -f logs/ python enjoy.py --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do: ``` python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga claterza -f logs/ rl_zoo3 enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` ## Training (with the RL Zoo) ``` python train.py --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ # Upload the model and generate video (when possible) python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga claterza ``` ## Hyperparameters ```python OrderedDict([('batch_size', 32), ('buffer_size', 100000), ('env_wrapper', ['stable_baselines3.common.atari_wrappers.AtariWrapper']), ('exploration_final_eps', 0.01), ('exploration_fraction', 0.1), ('frame_stack', 4), ('gradient_steps', 1), ('learning_rate', 0.0001), ('learning_starts', 100000), ('n_timesteps', 1000000.0), ('optimize_memory_usage', False), ('policy', 'CnnPolicy'), ('target_update_interval', 1000), ('train_freq', 4), ('normalize', False)]) ```
ittailup/lallama-13b-lora	ittailup	"2023-08-13T22:55:06Z"	0	0	peft	[ "peft", "region:us" ]	null	"2023-08-13T22:53:53Z"	--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.5.0.dev0
zyoscovits/phrasebank-sentiment-analysis	zyoscovits	"2023-10-26T19:24:03Z"	103	0	transformers	[ "transformers", "pytorch", "bert", "text-classification", "generated_from_trainer", "dataset:financial_phrasebank", "base_model:google-bert/bert-base-uncased", "base_model:finetune:google-bert/bert-base-uncased", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	"2023-10-26T19:23:40Z"	--- license: apache-2.0 base_model: bert-base-uncased tags: - generated_from_trainer datasets: - financial_phrasebank metrics: - f1 - accuracy model-index: - name: phrasebank-sentiment-analysis results: - task: name: Text Classification type: text-classification dataset: name: financial_phrasebank type: financial_phrasebank config: sentences_50agree split: train args: sentences_50agree metrics: - name: F1 type: f1 value: 0.8486113627644013 - name: Accuracy type: accuracy value: 0.8624484181568088 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # phrasebank-sentiment-analysis This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the financial_phrasebank dataset. It achieves the following results on the evaluation set: - Loss: 0.5636 - F1: 0.8486 - Accuracy: 0.8624 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 32 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 4 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:------:\|:--------:\| \| 0.5724 \| 0.94 \| 100 \| 0.3946 \| 0.8310 \| 0.8508 \| \| 0.2665 \| 1.89 \| 200 \| 0.3415 \| 0.8520 \| 0.8618 \| \| 0.1302 \| 2.83 \| 300 \| 0.4812 \| 0.8543 \| 0.8686 \| \| 0.0548 \| 3.77 \| 400 \| 0.5636 \| 0.8486 \| 0.8624 \| ### Framework versions - Transformers 4.34.1 - Pytorch 2.1.0+cu118 - Datasets 2.14.6 - Tokenizers 0.14.1
pszemraj/opt-125m-email-generation	pszemraj	"2023-11-19T22:19:09Z"	218	2	transformers	[ "transformers", "pytorch", "safetensors", "opt", "text-generation", "generated_from_trainer", "custom-license", "non-commercial", "email", "auto-complete", "125m", "dataset:aeslc", "base_model:facebook/opt-125m", "base_model:finetune:facebook/opt-125m", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2022-07-10T01:24:47Z"	--- license: other tags: - generated_from_trainer - opt - custom-license - non-commercial - email - auto-complete - 125m datasets: - aeslc widget: - text: 'Hey <NAME>, Thank you for signing up for my weekly newsletter. Before we get started, you''ll have to confirm your email address.' example_title: newsletter - text: 'Hi <NAME>, I hope this email finds you well. Let me start by saying that I am a big fan of your work.' example_title: fan - text: 'Greetings <NAME>, I hope you had a splendid evening at the Company sausage eating festival. I am reaching out because' example_title: festival - text: 'Good Morning <NAME>, I was just thinking to myself about how much I love creating value' example_title: value - text: URGENT - I need example_title: URGENT parameters: min_length: 4 max_length: 64 length_penalty: 0.7 no_repeat_ngram_size: 3 do_sample: false num_beams: 4 early_stopping: true repetition_penalty: 3.5 use_fast: false base_model: facebook/opt-125m --- > NOTE: there is currently a bug with huggingface API for OPT models. Please use the [colab notebook](https://colab.research.google.com/gist/pszemraj/033dc9a38da31ced7a0343091ba42e31/email-autocomplete-demo-125m.ipynb) to test :) # opt for email generation - 125m Why write the rest of your email when you can generate it? ``` from transformers import pipeline model_tag = "pszemraj/opt-125m-email-generation" generator = pipeline( 'text-generation', model=model_tag, use_fast=False, do_sample=False, ) prompt = """ Hello, Following up on the bubblegum shipment.""" generator( prompt, max_length=96, ) # generate ``` - [colab notebook](https://colab.research.google.com/gist/pszemraj/033dc9a38da31ced7a0343091ba42e31/email-autocomplete-demo-125m.ipynb) for testing/use ## About This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on an `aeslc` dataset. - Emails, phone numbers, etc., were attempted to be excluded in a dataset preparation step using [clean-text](https://pypi.org/project/clean-text/) in Python. - Note that API is restricted to generating 64 tokens - you can generate longer emails by using this in a text-generation `pipeline` object It achieves the following results on the evaluation set: - Loss: 2.5552 ## Intended uses & limitations - OPT models cannot be used commercially - [here is a GitHub gist](https://gist.github.com/pszemraj/c1b0a76445418b6bbddd5f9633d1bb7f) for a script to generate emails in the console or to a text file. ## Training and evaluation data - the `email_body` field of train + validation (get more data) from the [aeslc](https://huggingface.co/datasets/aeslc) dataset. ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 2.8245 \| 1.0 \| 129 \| 2.8030 \| \| 2.521 \| 2.0 \| 258 \| 2.6343 \| \| 2.2074 \| 3.0 \| 387 \| 2.5595 \| \| 2.0145 \| 4.0 \| 516 \| 2.5552 \| ### Framework versions - Transformers 4.20.1 - Pytorch 1.11.0+cu113 - Tokenizers 0.12.1
Cartinoe5930/Einstein-v4-7B_weight_diff	Cartinoe5930	"2024-06-23T04:05:51Z"	8	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2024-06-23T04:03:03Z"	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
bassemessam/Arabic-bank77-intent-classification	bassemessam	"2024-05-06T16:50:01Z"	107	0	transformers	[ "transformers", "safetensors", "bert", "text-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	"2024-04-30T14:27:26Z"	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
fedovtt/f05cd706-9db0-47af-8fdb-c64b24fbfa6c	fedovtt	"2025-01-18T23:42:28Z"	10	0	peft	[ "peft", "safetensors", "llama", "axolotl", "generated_from_trainer", "base_model:samoline/f6a49c16-f6d5-4405-a50a-9f416357ffe3", "base_model:adapter:samoline/f6a49c16-f6d5-4405-a50a-9f416357ffe3", "region:us" ]	null	"2025-01-18T23:35:43Z"	--- library_name: peft base_model: samoline/f6a49c16-f6d5-4405-a50a-9f416357ffe3 tags: - axolotl - generated_from_trainer model-index: - name: f05cd706-9db0-47af-8fdb-c64b24fbfa6c results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.4.1` ```yaml adapter: lora base_model: samoline/f6a49c16-f6d5-4405-a50a-9f416357ffe3 bf16: auto chat_template: llama3 dataset_prepared_path: null datasets: - data_files: - train_c4393383-ef1d-4e9c-b95c-18b4f735570d.json ds_type: json format: custom path: /workspace/input_data/train_c4393383-ef1d-4e9c-b95c-18b4f735570d.json type: field_input: input field_instruction: instruction field_output: output format: '{instruction} {input}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null device: cuda early_stopping_patience: 1 eval_max_new_tokens: 128 eval_steps: 5 eval_table_size: null evals_per_epoch: null flash_attention: false fp16: null gradient_accumulation_steps: 4 gradient_checkpointing: true group_by_length: false hub_model_id: fedovtt/f05cd706-9db0-47af-8fdb-c64b24fbfa6c hub_repo: null hub_strategy: checkpoint hub_token: null learning_rate: 0.0002 load_in_4bit: false load_in_8bit: false local_rank: null logging_steps: 3 lora_alpha: 32 lora_dropout: 0.05 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 16 lora_target_linear: true lr_scheduler: cosine max_memory: 0: 78GiB max_steps: 30 micro_batch_size: 2 mlflow_experiment_name: /tmp/train_c4393383-ef1d-4e9c-b95c-18b4f735570d.json model_type: AutoModelForCausalLM num_epochs: 1 optimizer: adamw_torch output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false save_steps: 10 sequence_len: 1024 strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: true trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: 22bf9415-03e7-41f5-b432-a11c378f3057 wandb_project: Gradients-On-Demand wandb_run: your_name wandb_runid: 22bf9415-03e7-41f5-b432-a11c378f3057 warmup_steps: 10 weight_decay: 0.01 xformers_attention: true ``` </details><br> # f05cd706-9db0-47af-8fdb-c64b24fbfa6c This model is a fine-tuned version of [samoline/f6a49c16-f6d5-4405-a50a-9f416357ffe3](https://huggingface.co/samoline/f6a49c16-f6d5-4405-a50a-9f416357ffe3) on the None dataset. It achieves the following results on the evaluation set: - Loss: nan ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 10 - training_steps: 30 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| No log \| 0.0002 \| 1 \| nan \| \| 0.0 \| 0.0010 \| 5 \| nan \| \| 0.0 \| 0.0020 \| 10 \| nan \| \| 0.0 \| 0.0031 \| 15 \| nan \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
PrunaAI/hrnet_w18.ms_aug_in1k-turbo-green-smashed	PrunaAI	"2024-08-02T15:30:28Z"	1	0	pruna-engine	[ "pruna-engine", "region:us" ]	null	"2024-03-10T03:51:38Z"	--- library_name: pruna-engine thumbnail: "https://assets-global.website-files.com/646b351987a8d8ce158d1940/64ec9e96b4334c0e1ac41504_Logo%20with%20white%20text.svg" metrics: - memory_disk - memory_inference - inference_latency - inference_throughput - inference_CO2_emissions - inference_energy_consumption --- <!-- header start --> <!-- 200823 --> <div style="width: auto; margin-left: auto; margin-right: auto"> <a href="https://www.pruna.ai/" target="_blank" rel="noopener noreferrer"> <img src="https://i.imgur.com/eDAlcgk.png" alt="PrunaAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </a> </div> <!-- header end --> [![Twitter](https://img.shields.io/twitter/follow/PrunaAI?style=social)](https://twitter.com/PrunaAI) [![GitHub](https://img.shields.io/github/followers/PrunaAI?label=Follow%20%40PrunaAI&style=social)](https://github.com/PrunaAI) [![LinkedIn](https://img.shields.io/badge/LinkedIn-Connect-blue)](https://www.linkedin.com/company/93832878/admin/feed/posts/?feedType=following) [![Discord](https://img.shields.io/badge/Discord-Join%20Us-blue?style=social&logo=discord)](https://discord.gg/rskEr4BZJx) # Simply make AI models cheaper, smaller, faster, and greener! - Give a thumbs up if you like this model! - Contact us and tell us which model to compress next [here](https://www.pruna.ai/contact). - Request access to easily compress your own AI models [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai). - Read the documentations to know more [here](https://pruna-ai-pruna.readthedocs-hosted.com/en/latest/) - Join Pruna AI community on Discord [here](https://discord.gg/rskEr4BZJx) to share feedback/suggestions or get help. ## Results ![image info](./plots.png) Frequently Asked Questions - *How does the compression work?* The model is compressed by combining quantization, xformers, jit, cuda graphs, triton. - *How does the model quality change?* The quality of the model output might slightly vary compared to the base model. - *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in `model/smash_config.json` and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you. - *What is the model format?* We used a custom Pruna model format based on pickle to make models compatible with the compression methods. We provide a tutorial to run models in dockers in the documentation [here](https://pruna-ai-pruna.readthedocs-hosted.com/en/latest/) if needed. - *What is the naming convention for Pruna Huggingface models?* We take the original model name and append "turbo", "tiny", or "green" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model. - *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai). - *What are "first" metrics?* Results mentioning "first" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads. - *What are "Sync" and "Async" metrics?* "Sync" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. "Async" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases. ## Setup You can run the smashed model with these steps: 0. Check that you have linux, python 3.10, and cuda 12.1.0 requirements installed. For cuda, check with `nvcc --version` and install with `conda install nvidia/label/cuda-12.1.0::cuda`. 1. Install the `pruna-engine` available [here](https://pypi.org/project/pruna-engine/) on Pypi. It might take up to 15 minutes to install. ```bash pip install pruna-engine[gpu]==0.7.1 --extra-index-url https://pypi.nvidia.com --extra-index-url https://pypi.ngc.nvidia.com --extra-index-url https://prunaai.pythonanywhere.com/ ``` 2. Download the model files using one of these three options. - Option 1 - Use command line interface (CLI): ```bash mkdir hrnet_w18.ms_aug_in1k-turbo-green-smashed huggingface-cli download PrunaAI/hrnet_w18.ms_aug_in1k-turbo-green-smashed --local-dir hrnet_w18.ms_aug_in1k-turbo-green-smashed --local-dir-use-symlinks False ``` - Option 2 - Use Python: ```python import subprocess repo_name = "hrnet_w18.ms_aug_in1k-turbo-green-smashed" subprocess.run(["mkdir", repo_name]) subprocess.run(["huggingface-cli", "download", 'PrunaAI/'+ repo_name, "--local-dir", repo_name, "--local-dir-use-symlinks", "False"]) ``` - Option 3 - Download them manually on the HuggingFace model page. 3. Load & run the model. ```python from pruna_engine.PrunaModel import PrunaModel model_path = "hrnet_w18.ms_aug_in1k-turbo-green-smashed/model" # Specify the downloaded model path. smashed_model = PrunaModel.load_model(model_path) # Load the model. import torch; image = torch.rand(1, 3, 224, 224).to('cuda') smashed_model(image) ``` ## Configurations The configuration info are in `model/smash_config.json`. ## Credits & License The license of the smashed model follows the license of the original model. Please check the license of the original model hrnet_w18.ms_aug_in1k before using this model which provided the base model. The license of the `pruna-engine` is [here](https://pypi.org/project/pruna-engine/) on Pypi. ## Want to compress other models? - Contact us and tell us which model to compress next [here](https://www.pruna.ai/contact). - Request access to easily compress your own AI models [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai).
booydar/RMT-Llama-3.2-1B-Instruct-2x1024-mem16-lora-babilong-qa1-5_ct-v2	booydar	"2024-12-23T12:39:44Z"	5	0	null	[ "safetensors", "model_hub_mixin", "pytorch_model_hub_mixin", "region:us" ]	null	"2024-12-23T12:35:57Z"	--- tags: - model_hub_mixin - pytorch_model_hub_mixin --- This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration: - Library: [More Information Needed] - Docs: [More Information Needed]
davidschulte/ESM_tab_fact_tab_fact_new	davidschulte	"2025-03-25T12:12:40Z"	14	0	null	[ "safetensors", "embedding_space_map", "BaseLM:bert-base-multilingual-uncased", "dataset:wenhu/tab_fact", "base_model:google-bert/bert-base-multilingual-uncased", "base_model:finetune:google-bert/bert-base-multilingual-uncased", "license:apache-2.0", "region:us" ]	null	"2025-01-08T17:01:17Z"	--- base_model: bert-base-multilingual-uncased datasets: - wenhu/tab_fact license: apache-2.0 tags: - embedding_space_map - BaseLM:bert-base-multilingual-uncased --- # ESM wenhu/tab_fact <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> ESM - Developed by: David Schulte - Model type: ESM - Base Model: bert-base-multilingual-uncased - Intermediate Task: wenhu/tab_fact - ESM architecture: linear - ESM embedding dimension: 768 - Language(s) (NLP): [More Information Needed] - License: Apache-2.0 license - ESM version: 0.1.0 ## Training Details ### Intermediate Task - Task ID: wenhu/tab_fact - Subset [optional]: tab_fact - Text Column: table_text - Label Column: label - Dataset Split: train - Sample size [optional]: 10000 - Sample seed [optional]: 42 ### Training Procedure [optional] <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Language Model Training Hyperparameters [optional] - Epochs: 3 - Batch size: 32 - Learning rate: 2e-05 - Weight Decay: 0.01 - Optimizer: AdamW ### ESM Training Hyperparameters [optional] - Epochs: 10 - Batch size: 32 - Learning rate: 0.001 - Weight Decay: 0.01 - Optimizer: AdamW ### Additional trainiung details [optional] ## Model evaluation ### Evaluation of fine-tuned language model [optional] ### Evaluation of ESM [optional] MSE: ### Additional evaluation details [optional] ## What are Embedding Space Maps used for? Embedding Space Maps are a part of ESM-LogME, a efficient method for finding intermediate datasets for transfer learning. There are two reasons to use ESM-LogME: ### You don't have enough training data for your problem If you don't have a enough training data for your problem, just use ESM-LogME to find more. You can supplement model training by including publicly available datasets in the training process. 1. Fine-tune a language model on suitable intermediate dataset. 2. Fine-tune the resulting model on your target dataset. This workflow is called intermediate task transfer learning and it can significantly improve the target performance. But what is a suitable dataset for your problem? ESM-LogME enable you to quickly rank thousands of datasets on the Hugging Face Hub by how well they are exptected to transfer to your target task. ### You want to find similar datasets to your target dataset Using ESM-LogME can be used like search engine on the Hugging Face Hub. You can find similar tasks to your target task without having to rely on heuristics. ESM-LogME estimates how language models fine-tuned on each intermediate task would benefinit your target task. This quantitative approach combines the effects of domain similarity and task similarity. ## How can I use ESM-LogME / ESMs? [![PyPI version](https://img.shields.io/pypi/v/hf-dataset-selector.svg)](https://pypi.org/project/hf-dataset-selector) We release hf-dataset-selector, a Python package for intermediate task selection using Embedding Space Maps. hf-dataset-selector fetches ESMs for a given language model and uses it to find the best dataset for applying intermediate training to the target task. ESMs are found by their tags on the Huggingface Hub. ```python from hfselect import Dataset, compute_task_ranking # Load target dataset from the Hugging Face Hub dataset = Dataset.from_hugging_face( name="stanfordnlp/imdb", split="train", text_col="text", label_col="label", is_regression=False, num_examples=1000, seed=42 ) # Fetch ESMs and rank tasks task_ranking = compute_task_ranking( dataset=dataset, model_name="bert-base-multilingual-uncased" ) # Display top 5 recommendations print(task_ranking[:5]) ``` ```python 1. davanstrien/test_imdb_embedd2 Score: -0.618529 2. davanstrien/test_imdb_embedd Score: -0.618644 3. davanstrien/test1 Score: -0.619334 4. stanfordnlp/imdb Score: -0.619454 5. stanfordnlp/sst Score: -0.62995 ``` \| Rank \| Task ID \| Task Subset \| Text Column \| Label Column \| Task Split \| Num Examples \| ESM Architecture \| Score \| \|-------:\|:------------------------------\|:----------------\|:--------------\|:---------------\|:-------------\|---------------:\|:-------------------\|----------:\| \| 1 \| davanstrien/test_imdb_embedd2 \| default \| text \| label \| train \| 10000 \| linear \| -0.618529 \| \| 2 \| davanstrien/test_imdb_embedd \| default \| text \| label \| train \| 10000 \| linear \| -0.618644 \| \| 3 \| davanstrien/test1 \| default \| text \| label \| train \| 10000 \| linear \| -0.619334 \| \| 4 \| stanfordnlp/imdb \| plain_text \| text \| label \| train \| 10000 \| linear \| -0.619454 \| \| 5 \| stanfordnlp/sst \| dictionary \| phrase \| label \| dictionary \| 10000 \| linear \| -0.62995 \| \| 6 \| stanfordnlp/sst \| default \| sentence \| label \| train \| 8544 \| linear \| -0.63312 \| \| 7 \| kuroneko5943/snap21 \| CDs_and_Vinyl_5 \| sentence \| label \| train \| 6974 \| linear \| -0.634365 \| \| 8 \| kuroneko5943/snap21 \| Video_Games_5 \| sentence \| label \| train \| 6997 \| linear \| -0.638787 \| \| 9 \| kuroneko5943/snap21 \| Movies_and_TV_5 \| sentence \| label \| train \| 6989 \| linear \| -0.639068 \| \| 10 \| fancyzhx/amazon_polarity \| amazon_polarity \| content \| label \| train \| 10000 \| linear \| -0.639718 \| For more information on how to use ESMs please have a look at the [official Github repository](https://github.com/davidschulte/hf-dataset-selector). We provide documentation further documentation and tutorials for finding intermediate datasets and training your own ESMs. ## How do Embedding Space Maps work? <!-- This section describes the evaluation protocols and provides the results. --> Embedding Space Maps (ESMs) are neural networks that approximate the effect of fine-tuning a language model on a task. They can be used to quickly transform embeddings from a base model to approximate how a fine-tuned model would embed the the input text. ESMs can be used for intermediate task selection with the ESM-LogME workflow. ## How can I use Embedding Space Maps for Intermediate Task Selection? ## Citation <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> If you are using this Embedding Space Maps, please cite our [paper](https://aclanthology.org/2024.emnlp-main.529/). BibTeX: ``` @inproceedings{schulte-etal-2024-less, title = "Less is More: Parameter-Efficient Selection of Intermediate Tasks for Transfer Learning", author = "Schulte, David and Hamborg, Felix and Akbik, Alan", editor = "Al-Onaizan, Yaser and Bansal, Mohit and Chen, Yun-Nung", booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing", month = nov, year = "2024", address = "Miami, Florida, USA", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2024.emnlp-main.529/", doi = "10.18653/v1/2024.emnlp-main.529", pages = "9431--9442", abstract = "Intermediate task transfer learning can greatly improve model performance. If, for example, one has little training data for emotion detection, first fine-tuning a language model on a sentiment classification dataset may improve performance strongly. But which task to choose for transfer learning? Prior methods producing useful task rankings are infeasible for large source pools, as they require forward passes through all source language models. We overcome this by introducing Embedding Space Maps (ESMs), light-weight neural networks that approximate the effect of fine-tuning a language model. We conduct the largest study on NLP task transferability and task selection with 12k source-target pairs. We find that applying ESMs on a prior method reduces execution time and disk space usage by factors of 10 and 278, respectively, while retaining high selection performance (avg. regret@5 score of 2.95)." } ``` APA: ``` Schulte, D., Hamborg, F., & Akbik, A. (2024, November). Less is More: Parameter-Efficient Selection of Intermediate Tasks for Transfer Learning. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (pp. 9431-9442). ``` ## Additional Information
vocabtrimmer/mt5-small-itquad-qg-trimmed-it-30000	vocabtrimmer	"2023-03-15T11:12:32Z"	3	0	transformers	[ "transformers", "pytorch", "mt5", "text2text-generation", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text2text-generation	"2023-03-15T10:59:37Z"	# Vocabulary Trimmed [lmqg/mt5-small-itquad-qg](https://huggingface.co/lmqg/mt5-small-itquad-qg): `vocabtrimmer/mt5-small-itquad-qg-trimmed-it-30000` This model is a trimmed version of [lmqg/mt5-small-itquad-qg](https://huggingface.co/lmqg/mt5-small-itquad-qg) by [`vocabtrimmer`](https://github.com/asahi417/lm-vocab-trimmer), a tool for trimming vocabulary of language models to compress the model size. Following table shows a summary of the trimming process. \| \| lmqg/mt5-small-itquad-qg \| vocabtrimmer/mt5-small-itquad-qg-trimmed-it-30000 \| \|:---------------------------\|:---------------------------\|:----------------------------------------------------\| \| parameter_size_full \| 300,165,504 \| 74,784,128 \| \| parameter_size_embedding \| 256,103,424 \| 30,722,048 \| \| vocab_size \| 250,101 \| 30,002 \| \| compression_rate_full \| 100.0 \| 24.91 \| \| compression_rate_embedding \| 100.0 \| 12.0 \| Following table shows the parameter used to trim vocabulary. \| language \| dataset \| dataset_column \| dataset_name \| dataset_split \| target_vocab_size \| min_frequency \| \|:-----------\|:----------------------------\|:-----------------\|:---------------\|:----------------\|--------------------:\|----------------:\| \| it \| vocabtrimmer/mc4_validation \| text \| it \| validation \| 30000 \| 2 \|
XelotX/Tess-v2.5.2-Qwen2-72B-XelotX-Quants-BF16	XelotX	"2024-07-12T16:28:28Z"	4	0	null	[ "gguf", "text-generation", "license:other", "endpoints_compatible", "region:us", "conversational" ]	text-generation	"2024-07-12T16:28:28Z"	--- license: other license_name: qwen2 license_link: https://huggingface.co/Qwen/Qwen2-72B/blob/main/LICENSE quantized_by: bartowski pipeline_tag: text-generation --- ## Llamacpp imatrix Quantizations of Tess-v2.5.2-Qwen2-72B Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3145">b3145</a> for quantization. Original model: https://huggingface.co/migtissera/Tess-v2.5.2-Qwen2-72B All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) ## Prompt format ``` <\|im_start\|>system {system_prompt}<\|im_end\|> <\|im_start\|>user {prompt}<\|im_end\|> <\|im_start\|>assistant ``` ## Download a file (not the whole branch) from below: \| Filename \| Quant type \| File Size \| Description \| \| -------- \| ---------- \| --------- \| ----------- \| \| [Tess-v2.5.2-Qwen2-72B-Q8_0.gguf](https://huggingface.co/bartowski/Tess-v2.5.2-Qwen2-72B-GGUF/tree/main/Tess-v2.5.2-Qwen2-72B-Q8_0.gguf) \| Q8_0 \| 79.59GB \| Extremely high quality, generally unneeded but max available quant. \| \| [Tess-v2.5.2-Qwen2-72B-Q5_K_M.gguf](https://huggingface.co/bartowski/Tess-v2.5.2-Qwen2-72B-GGUF/tree/main/Tess-v2.5.2-Qwen2-72B-Q5_K_M.gguf) \| Q5_K_M \| 57.55GB \| High quality, recommended. \| \| [Tess-v2.5.2-Qwen2-72B-Q4_K_M.gguf](https://huggingface.co/bartowski/Tess-v2.5.2-Qwen2-72B-GGUF/tree/main/Tess-v2.5.2-Qwen2-72B-Q4_K_M.gguf) \| Q4_K_M \| 50.67GB \| Good quality, uses about 4.83 bits per weight, recommended. \| \| [Tess-v2.5.2-Qwen2-72B-IQ4_XS.gguf](https://huggingface.co/bartowski/Tess-v2.5.2-Qwen2-72B-GGUF/blob/main/Tess-v2.5.2-Qwen2-72B-IQ4_XS.gguf) \| IQ4_XS \| 43.00GB \| Decent quality, smaller than Q4_K_S with similar performance, recommended. \| \| [Tess-v2.5.2-Qwen2-72B-Q3_K_M.gguf](https://huggingface.co/bartowski/Tess-v2.5.2-Qwen2-72B-GGUF/blob/main/Tess-v2.5.2-Qwen2-72B-Q3_K_M.gguf) \| Q3_K_M \| 41.12GB \| Even lower quality. \| \| [Tess-v2.5.2-Qwen2-72B-IQ3_M.gguf](https://huggingface.co/bartowski/Tess-v2.5.2-Qwen2-72B-GGUF/blob/main/Tess-v2.5.2-Qwen2-72B-IQ3_M.gguf) \| IQ3_M \| 38.92GB \| Medium-low quality, new method with decent performance comparable to Q3_K_M. \| \| [Tess-v2.5.2-Qwen2-72B-Q3_K_S.gguf](https://huggingface.co/bartowski/Tess-v2.5.2-Qwen2-72B-GGUF/blob/main/Tess-v2.5.2-Qwen2-72B-Q3_K_S.gguf) \| Q3_K_S \| 37.91GB \| Low quality, not recommended. \| \| [Tess-v2.5.2-Qwen2-72B-IQ3_XXS.gguf](https://huggingface.co/bartowski/Tess-v2.5.2-Qwen2-72B-GGUF/blob/main/Tess-v2.5.2-Qwen2-72B-IQ3_XXS.gguf) \| IQ3_XXS \| 35.43GB \| Lower quality, new method with decent performance, comparable to Q3 quants. \| \| [Tess-v2.5.2-Qwen2-72B-Q2_K.gguf](https://huggingface.co/bartowski/Tess-v2.5.2-Qwen2-72B-GGUF/blob/main/Tess-v2.5.2-Qwen2-72B-Q2_K.gguf) \| Q2_K \| 33.36GB \| Very low quality but surprisingly usable. \| \| [Tess-v2.5.2-Qwen2-72B-IQ2_M.gguf](https://huggingface.co/bartowski/Tess-v2.5.2-Qwen2-72B-GGUF/blob/main/Tess-v2.5.2-Qwen2-72B-IQ2_M.gguf) \| IQ2_M \| 32.93GB \| Very low quality, uses SOTA techniques to also be surprisingly usable. \| \| [Tess-v2.5.2-Qwen2-72B-IQ2_XS.gguf](https://huggingface.co/bartowski/Tess-v2.5.2-Qwen2-72B-GGUF/blob/main/Tess-v2.5.2-Qwen2-72B-IQ2_XS.gguf) \| IQ2_XS \| 30.77GB \| Lower quality, uses SOTA techniques to be usable. \| \| [Tess-v2.5.2-Qwen2-72B-IQ2_XXS.gguf](https://huggingface.co/bartowski/Tess-v2.5.2-Qwen2-72B-GGUF/blob/main/Tess-v2.5.2-Qwen2-72B-IQ2_XXS.gguf) \| IQ2_XXS \| 29.20GB \| Lower quality, uses SOTA techniques to be usable. \| \| [Tess-v2.5.2-Qwen2-72B-IQ1_M.gguf](https://huggingface.co/bartowski/Tess-v2.5.2-Qwen2-72B-GGUF/blob/main/Tess-v2.5.2-Qwen2-72B-IQ1_M.gguf) \| IQ1_M \| 27.45GB \| Extremely low quality, not recommended. \| ## Downloading using huggingface-cli First, make sure you have hugginface-cli installed: ``` pip install -U "huggingface_hub[cli]" ``` Then, you can target the specific file you want: ``` huggingface-cli download bartowski/Tess-v2.5.2-Qwen2-72B-GGUF --include "Tess-v2.5.2-Qwen2-72B-Q4_K_M.gguf" --local-dir ./ ``` If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run: ``` huggingface-cli download bartowski/Tess-v2.5.2-Qwen2-72B-GGUF --include "Tess-v2.5.2-Qwen2-72B-Q8_0.gguf/" --local-dir Tess-v2.5.2-Qwen2-72B-Q8_0 ``` You can either specify a new local-dir (Tess-v2.5.2-Qwen2-72B-Q8_0) or download them all in place (./) ## Which file should I choose? A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have. If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM. If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total. Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'. If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M. If you want to get more into the weeds, you can check out this extremely useful feature chart: [llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix) But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size. These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide. The I-quants are not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm. Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
keras/deeplab_v3_plus_resnet50_pascalvoc	keras	"2025-03-24T22:40:07Z"	231	1	keras-hub	[ "keras-hub", "image-segmentation", "arxiv:1802.02611", "license:apache-2.0", "region:us" ]	image-segmentation	"2024-10-28T20:10:29Z"	--- library_name: keras-hub license: apache-2.0 tags: - image-segmentation pipeline_tag: image-segmentation --- ### Model Overview DeepLabv3+ model is developed by Google for semantic segmentation. This guide demonstrates how to finetune and use DeepLabv3+ model for image semantic segmentaion with KerasCV. Its architecture that combines atrous convolutions, contextual information aggregation, and powerful backbones to achieve accurate and detailed semantic segmentation. The DeepLabv3+ model has been shown to achieve state-of-the-art results on a variety of image segmentation benchmarks. This model is supported in both KerasCV and KerasHub. KerasCV will no longer be actively developed, so please try to use KerasHub. ` Weights are released under the [Apache 2 License](https://apache.org/licenses/LICENSE-2.0). Keras model code is released under the [Apache 2 License](https://github.com/keras-team/keras-hub/blob/master/LICENSE). ## Links * [DeepLabV3Plus Quickstart Notebook](https://www.kaggle.com/code/prasadsachin/deeplabv3plus-quickstart) * [DeepLabV3Plus Finetune Notebook](https://www.kaggle.com/code/prasadsachin/deeplabv3plus-finetune-notebook/) * [DeepLabV3Plus API Documentation](https://keras.io/api/keras_hub/models/deeplab_v3/) * [KerasHub Beginner Guide](https://keras.io/guides/keras_hub/getting_started/) * [KerasHub Model Publishing Guide](https://keras.io/guides/keras_hub/upload/) ## Installation Keras and KerasHub can be installed with: ``` pip install -U -q keras-hub pip install -U -q keras ``` Jax, TensorFlow, and Torch come preinstalled in Kaggle Notebooks. For instructions on installing them in another environment see the [Keras Getting Started](https://keras.io/getting_started/) page. ## Presets The following model checkpoints are provided by the Keras team. Full code examples for each are available below. \| Preset name \| Parameters \| Description \| \|------------------------------------\|------------\|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\| \| deeplab_v3_plus_resnet50_pascalvoc \| 39.1M \| DeeplabV3Plus with a ResNet50 v2 backbone. Trained on PascalVOC 2012 Semantic segmentation task, which consists of 20 classes and one background class. This model achieves a final categorical accuracy of 89.34% and mIoU of 0.6391 on evaluation dataset. This preset is only comptabile with Keras 3. \| ## Model card https://arxiv.org/abs/1802.02611 ## Example Usage Load DeepLabv3+ presets a extension of DeepLabv3 by adding a simple yet effective decoder module to refine the segmentation results especially along object boundaries. ```python images = np.ones(shape=(1, 96, 96, 3)) labels = np.zeros(shape=(1, 96, 96, 2)) segmenter = keras_hub.models.DeepLabV3ImageSegmenter.from_preset( "deeplab_v3_plus_resnet50_pascalvoc", ) segmenter.predict(images) ``` Specify `num_classes` to load randomly initialized segmentation head. ```python segmenter = keras_hub.models.DeepLabV3ImageSegmenter.from_preset( "deeplab_v3_plus_resnet50_pascalvoc", num_classes=2, ) segmenter.preprocessor.image_size = (96, 96) segmenter.fit(images, labels, epochs=3) segmenter.predict(images) # Trained 2 class segmentation. ``` ## Example Usage with Hugging Face URI Load DeepLabv3+ presets a extension of DeepLabv3 by adding a simple yet effective decoder module to refine the segmentation results especially along object boundaries. ```python images = np.ones(shape=(1, 96, 96, 3)) labels = np.zeros(shape=(1, 96, 96, 2)) segmenter = keras_hub.models.DeepLabV3ImageSegmenter.from_preset( "hf://keras/deeplab_v3_plus_resnet50_pascalvoc", ) segmenter.predict(images) ``` Specify `num_classes` to load randomly initialized segmentation head. ```python segmenter = keras_hub.models.DeepLabV3ImageSegmenter.from_preset( "hf://keras/deeplab_v3_plus_resnet50_pascalvoc", num_classes=2, ) segmenter.preprocessor.image_size = (96, 96) segmenter.fit(images, labels, epochs=3) segmenter.predict(images) # Trained 2 class segmentation. ```
ksmcg/controlnet-room-seg	ksmcg	"2023-04-26T11:11:12Z"	0	0	diffusers	[ "diffusers", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "controlnet", "jax-diffusers-event", "base_model:runwayml/stable-diffusion-v1-5", "base_model:adapter:runwayml/stable-diffusion-v1-5", "license:creativeml-openrail-m", "region:us" ]	text-to-image	"2023-04-26T07:48:55Z"	--- license: creativeml-openrail-m base_model: runwayml/stable-diffusion-v1-5 tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - controlnet - jax-diffusers-event inference: true --- # controlnet- ksmcg/controlnet-room-seg These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning. You can find some example images in the following.
sd-concepts-library/between2-mt-fade	sd-concepts-library	"2022-09-09T18:20:56Z"	0	2	null	[ "license:mit", "region:us" ]	null	"2022-09-09T18:12:25Z"	--- license: mit --- ### between2 MT fade on Stable Diffusion This is the `<b2MTfade>` concept taught to Stable Diffusion via Textual Inversion. You can load this concept into the [Stable Conceptualizer](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/stable_conceptualizer_inference.ipynb) notebook. You can also train your own concepts and load them into the concept libraries using [this notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_textual_inversion_training.ipynb). Here is the new concept you will be able to use as a `style`: ![<b2MTfade> 0](https://huggingface.co/sd-concepts-library/between2-mt-fade/resolve/main/concept_images/0.jpeg) ![<b2MTfade> 1](https://huggingface.co/sd-concepts-library/between2-mt-fade/resolve/main/concept_images/1.jpeg) ![<b2MTfade> 2](https://huggingface.co/sd-concepts-library/between2-mt-fade/resolve/main/concept_images/2.jpeg) ![<b2MTfade> 3](https://huggingface.co/sd-concepts-library/between2-mt-fade/resolve/main/concept_images/3.jpeg) ![<b2MTfade> 4](https://huggingface.co/sd-concepts-library/between2-mt-fade/resolve/main/concept_images/4.jpeg) ![<b2MTfade> 5](https://huggingface.co/sd-concepts-library/between2-mt-fade/resolve/main/concept_images/5.jpeg) ![<b2MTfade> 6](https://huggingface.co/sd-concepts-library/between2-mt-fade/resolve/main/concept_images/6.jpeg) ![<b2MTfade> 7](https://huggingface.co/sd-concepts-library/between2-mt-fade/resolve/main/concept_images/7.jpeg) ![<b2MTfade> 8](https://huggingface.co/sd-concepts-library/between2-mt-fade/resolve/main/concept_images/8.jpeg) ![<b2MTfade> 9](https://huggingface.co/sd-concepts-library/between2-mt-fade/resolve/main/concept_images/9.jpeg) ![<b2MTfade> 10](https://huggingface.co/sd-concepts-library/between2-mt-fade/resolve/main/concept_images/10.jpeg) ![<b2MTfade> 11](https://huggingface.co/sd-concepts-library/between2-mt-fade/resolve/main/concept_images/11.jpeg) ![<b2MTfade> 12](https://huggingface.co/sd-concepts-library/between2-mt-fade/resolve/main/concept_images/12.jpeg) ![<b2MTfade> 13](https://huggingface.co/sd-concepts-library/between2-mt-fade/resolve/main/concept_images/13.jpeg) ![<b2MTfade> 14](https://huggingface.co/sd-concepts-library/between2-mt-fade/resolve/main/concept_images/14.jpeg) ![<b2MTfade> 15](https://huggingface.co/sd-concepts-library/between2-mt-fade/resolve/main/concept_images/15.jpeg) ![<b2MTfade> 16](https://huggingface.co/sd-concepts-library/between2-mt-fade/resolve/main/concept_images/16.jpeg) ![<b2MTfade> 17](https://huggingface.co/sd-concepts-library/between2-mt-fade/resolve/main/concept_images/17.jpeg) ![<b2MTfade> 18](https://huggingface.co/sd-concepts-library/between2-mt-fade/resolve/main/concept_images/18.jpeg) ![<b2MTfade> 19](https://huggingface.co/sd-concepts-library/between2-mt-fade/resolve/main/concept_images/19.jpeg) ![<b2MTfade> 20](https://huggingface.co/sd-concepts-library/between2-mt-fade/resolve/main/concept_images/20.jpeg)
Aotsuyu/Soushiki	Aotsuyu	"2023-12-11T17:37:25Z"	0	7	null	[ "license:creativeml-openrail-m", "region:us" ]	null	"2023-11-21T02:52:04Z"	--- license: creativeml-openrail-m --- <center> <h1 style="font-size:1.6rem;"> <b> Soushiki （葬式） </b> </h1> </center> The model some previously may have downloaded as `9-AAAAAAA` is now renamed to SoushikiV0.9. For 1.0 I very slightly slightly increased finger separation (it doesn't necessarily mean better hands, rather it's less likely that hands become an eldritch mess). I bumped the vibrance a bit. Do not hang up on the versions too much, 0.9 might be more to your liking. ### previews <img src="https://huggingface.co/Aotsuyu/Soushiki/resolve/main/img/xyz_grid-0043-2155415307.png" width="50%"></img> <img src="https://huggingface.co/Aotsuyu/Soushiki/resolve/main/img/xyz_grid-0044-384282104.png" width="50%"></img> <img src="https://huggingface.co/Aotsuyu/Soushiki/resolve/main/img/xyz_grid-0048-3671274917.png" width="50%"></img> <img src="https://huggingface.co/Aotsuyu/Soushiki/resolve/main/img/xyz_grid-0049-73335132.png" width="50%"></img> <img src="https://huggingface.co/Aotsuyu/Soushiki/resolve/main/img/xyz_grid-0050-667165639.png" width="50%"></img> ### settings ~~Use whatever the fuck you want.~~ I keep my negative to `low quality, worst quality`, and usually use DPM++ 2M Karras or Restart samplers at 20-25 steps with 5-10 cfg. kl-f8-anime2 or a variant for VAE. ### ramblings Yet another fairly shizo merge. I started off from Gishiki, adding elements I liked from CTD's lovely connectmix3 and Jemnite's amazing TangYuanV3. This time I also utilized some artist LoRA and some diffLoRA to push the textures, contrast, details noise offset and such into directions I wanted. The artstyle loras were mostly mine, but I got some off of [Derrian](https://civitai.com/user/derriandistro/models) and one anon. I consider this less style neutral from what I usually go for, but I had no trouble using LoRAs with it. This is a product of autistic XYZ comparison and abusing supermerger and I find it satisfying for now. ### does this have new holos No, I can't be arsed to make a finetune from scratch, maybe sometime in the future that will change. Use this or whatever for holo advent https://huggingface.co/Aotsuyu/LoRA/blob/main/characters/%5Bchars%5D%20holoadventv5.safetensors
mshen2/llama3-8b-v4-short-em-up	mshen2	"2025-03-20T01:33:13Z"	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2025-03-20T01:29:51Z"	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
mradermacher/SASTRI_V0.1-i1-GGUF	mradermacher	"2024-11-16T08:55:09Z"	105	0	transformers	[ "transformers", "gguf", "hi", "en", "bh", "license:apache-2.0", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	null	"2024-11-16T07:12:07Z"	--- base_model: divyanshukunwar/SASTRI_V0.1 language: - hi - en - bh library_name: transformers license: apache-2.0 quantized_by: mradermacher --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/divyanshukunwar/SASTRI_V0.1 <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/SASTRI_V0.1-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/SASTRI_V0.1-i1-GGUF/resolve/main/SASTRI_V0.1.i1-IQ1_S.gguf) \| i1-IQ1_S \| 2.5 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/SASTRI_V0.1-i1-GGUF/resolve/main/SASTRI_V0.1.i1-IQ1_M.gguf) \| i1-IQ1_M \| 2.6 \| mostly desperate \| \| [GGUF](https://huggingface.co/mradermacher/SASTRI_V0.1-i1-GGUF/resolve/main/SASTRI_V0.1.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 2.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/SASTRI_V0.1-i1-GGUF/resolve/main/SASTRI_V0.1.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 3.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/SASTRI_V0.1-i1-GGUF/resolve/main/SASTRI_V0.1.i1-IQ2_S.gguf) \| i1-IQ2_S \| 3.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/SASTRI_V0.1-i1-GGUF/resolve/main/SASTRI_V0.1.i1-IQ2_M.gguf) \| i1-IQ2_M \| 3.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/SASTRI_V0.1-i1-GGUF/resolve/main/SASTRI_V0.1.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 3.9 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/SASTRI_V0.1-i1-GGUF/resolve/main/SASTRI_V0.1.i1-Q2_K.gguf) \| i1-Q2_K \| 3.9 \| IQ3_XXS probably better \| \| [GGUF](https://huggingface.co/mradermacher/SASTRI_V0.1-i1-GGUF/resolve/main/SASTRI_V0.1.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 4.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/SASTRI_V0.1-i1-GGUF/resolve/main/SASTRI_V0.1.i1-IQ3_S.gguf) \| i1-IQ3_S \| 4.4 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/SASTRI_V0.1-i1-GGUF/resolve/main/SASTRI_V0.1.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 4.4 \| IQ3_XS probably better \| \| [GGUF](https://huggingface.co/mradermacher/SASTRI_V0.1-i1-GGUF/resolve/main/SASTRI_V0.1.i1-IQ3_M.gguf) \| i1-IQ3_M \| 4.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/SASTRI_V0.1-i1-GGUF/resolve/main/SASTRI_V0.1.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 4.9 \| IQ3_S probably better \| \| [GGUF](https://huggingface.co/mradermacher/SASTRI_V0.1-i1-GGUF/resolve/main/SASTRI_V0.1.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 5.2 \| IQ3_M probably better \| \| [GGUF](https://huggingface.co/mradermacher/SASTRI_V0.1-i1-GGUF/resolve/main/SASTRI_V0.1.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 5.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/SASTRI_V0.1-i1-GGUF/resolve/main/SASTRI_V0.1.i1-Q4_0_4_4.gguf) \| i1-Q4_0_4_4 \| 5.5 \| fast on arm, low quality \| \| [GGUF](https://huggingface.co/mradermacher/SASTRI_V0.1-i1-GGUF/resolve/main/SASTRI_V0.1.i1-Q4_0_4_8.gguf) \| i1-Q4_0_4_8 \| 5.5 \| fast on arm+i8mm, low quality \| \| [GGUF](https://huggingface.co/mradermacher/SASTRI_V0.1-i1-GGUF/resolve/main/SASTRI_V0.1.i1-Q4_0_8_8.gguf) \| i1-Q4_0_8_8 \| 5.5 \| fast on arm+sve, low quality \| \| [GGUF](https://huggingface.co/mradermacher/SASTRI_V0.1-i1-GGUF/resolve/main/SASTRI_V0.1.i1-Q4_0.gguf) \| i1-Q4_0 \| 5.6 \| fast, low quality \| \| [GGUF](https://huggingface.co/mradermacher/SASTRI_V0.1-i1-GGUF/resolve/main/SASTRI_V0.1.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 5.6 \| optimal size/speed/quality \| \| [GGUF](https://huggingface.co/mradermacher/SASTRI_V0.1-i1-GGUF/resolve/main/SASTRI_V0.1.i1-Q4_K_M.gguf) \| i1-Q4_K_M \| 5.9 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/SASTRI_V0.1-i1-GGUF/resolve/main/SASTRI_V0.1.i1-Q5_K_S.gguf) \| i1-Q5_K_S \| 6.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/SASTRI_V0.1-i1-GGUF/resolve/main/SASTRI_V0.1.i1-Q5_K_M.gguf) \| i1-Q5_K_M \| 6.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/SASTRI_V0.1-i1-GGUF/resolve/main/SASTRI_V0.1.i1-Q6_K.gguf) \| i1-Q6_K \| 7.7 \| practically like static Q6_K \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. <!-- end -->
kylelovesllms/Wav2Vec2Ipa	kylelovesllms	"2024-12-09T03:18:36Z"	28	0	null	[ "pytorch", "wav2vec2", "generated_from_trainer", "dataset:timit_asr", "license:apache-2.0", "region:us" ]	null	"2024-11-07T23:21:07Z"	--- license: apache-2.0 tags: - generated_from_trainer datasets: - timit_asr model-index: - name: Wav2Vec2Ipa results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # Wav2Vec2Ipa This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the timit_asr dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 1000 - num_epochs: 30 - mixed_precision_training: Native AMP ### Framework versions - Transformers 4.17.0 - Pytorch 2.5.0+cu121 - Datasets 1.18.3 - Tokenizers 0.19.1
havinash-ai/f3309fbc-3fdd-47fe-9fba-87dd620d6cdc	havinash-ai	"2025-02-09T05:39:13Z"	9	0	peft	[ "peft", "safetensors", "llama", "axolotl", "generated_from_trainer", "base_model:unsloth/codellama-7b", "base_model:adapter:unsloth/codellama-7b", "license:apache-2.0", "region:us" ]	null	"2025-02-09T03:44:38Z"	--- library_name: peft license: apache-2.0 base_model: unsloth/codellama-7b tags: - axolotl - generated_from_trainer model-index: - name: f3309fbc-3fdd-47fe-9fba-87dd620d6cdc results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # f3309fbc-3fdd-47fe-9fba-87dd620d6cdc This model is a fine-tuned version of [unsloth/codellama-7b](https://huggingface.co/unsloth/codellama-7b) on the None dataset. It achieves the following results on the evaluation set: - Loss: nan ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
AlignmentResearch/robust_llm_pythia-tt-410m-mz-ada-v3-ch-135000	AlignmentResearch	"2024-03-22T22:13:04Z"	104	0	transformers	[ "transformers", "safetensors", "gpt_neox", "text-classification", "generated_from_trainer", "base_model:EleutherAI/pythia-410m-deduped", "base_model:finetune:EleutherAI/pythia-410m-deduped", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-classification	"2024-03-22T22:12:14Z"	--- license: apache-2.0 tags: - generated_from_trainer base_model: EleutherAI/pythia-410m-deduped model-index: - name: robust_llm_pythia-tt-410m-mz-ada-v3-ch-135000 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # robust_llm_pythia-tt-410m-mz-ada-v3-ch-135000 This model is a fine-tuned version of [EleutherAI/pythia-410m-deduped](https://huggingface.co/EleutherAI/pythia-410m-deduped) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 ### Training results ### Framework versions - Transformers 4.37.2 - Pytorch 2.2.0 - Datasets 2.17.0 - Tokenizers 0.15.2
Triangle104/EVA-abliterated-TIES-Qwen2.5-1.5B-Q6_K-GGUF	Triangle104	"2025-01-31T21:37:19Z"	22	0	transformers	[ "transformers", "gguf", "mergekit", "merge", "llama-cpp", "gguf-my-repo", "base_model:nbeerbower/EVA-abliterated-TIES-Qwen2.5-1.5B", "base_model:quantized:nbeerbower/EVA-abliterated-TIES-Qwen2.5-1.5B", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	"2025-01-31T21:37:10Z"	--- base_model: nbeerbower/EVA-abliterated-TIES-Qwen2.5-1.5B library_name: transformers tags: - mergekit - merge - llama-cpp - gguf-my-repo license: apache-2.0 --- # Triangle104/EVA-abliterated-TIES-Qwen2.5-1.5B-Q6_K-GGUF This model was converted to GGUF format from [`nbeerbower/EVA-abliterated-TIES-Qwen2.5-1.5B`](https://huggingface.co/nbeerbower/EVA-abliterated-TIES-Qwen2.5-1.5B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/nbeerbower/EVA-abliterated-TIES-Qwen2.5-1.5B) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo Triangle104/EVA-abliterated-TIES-Qwen2.5-1.5B-Q6_K-GGUF --hf-file eva-abliterated-ties-qwen2.5-1.5b-q6_k.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo Triangle104/EVA-abliterated-TIES-Qwen2.5-1.5B-Q6_K-GGUF --hf-file eva-abliterated-ties-qwen2.5-1.5b-q6_k.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo Triangle104/EVA-abliterated-TIES-Qwen2.5-1.5B-Q6_K-GGUF --hf-file eva-abliterated-ties-qwen2.5-1.5b-q6_k.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo Triangle104/EVA-abliterated-TIES-Qwen2.5-1.5B-Q6_K-GGUF --hf-file eva-abliterated-ties-qwen2.5-1.5b-q6_k.gguf -c 2048 ```
NghiemAbe/gpt-neo-vi-small-v6	NghiemAbe	"2024-03-28T06:34:53Z"	175	0	transformers	[ "transformers", "safetensors", "gpt_neo", "text-generation", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	"2023-12-07T13:16:27Z"	--- base_model: NghiemAbe/gpt-neo-vi-small-v5 tags: - generated_from_trainer model-index: - name: gpt-neo-vi-small-v6 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # gpt-neo-vi-small-v6 This model is a fine-tuned version of [NlpHUST/gpt-neo-vi-small](https://huggingface.co/NlpHUST/gpt-neo-vi-small) on an [ViQuad](https://huggingface.co/datasets/NghiemAbe/viquad) dataset. It achieves the following results on the evaluation set: - Loss: 0.4156 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0003 - train_batch_size: 2 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 64 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 100 - num_epochs: 1 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 0.3849 \| 0.1 \| 25 \| 0.5802 \| \| 0.3747 \| 0.19 \| 50 \| 0.5680 \| \| 0.3843 \| 0.29 \| 75 \| 0.5695 \| \| 0.4016 \| 0.39 \| 100 \| 0.5782 \| \| 0.4101 \| 0.49 \| 125 \| 0.5563 \| \| 0.4011 \| 0.58 \| 150 \| 0.5162 \| \| 0.3729 \| 0.68 \| 175 \| 0.4888 \| \| 0.3512 \| 0.78 \| 200 \| 0.4544 \| \| 0.316 \| 0.88 \| 225 \| 0.4319 \| \| 0.3126 \| 0.97 \| 250 \| 0.4156 \| ### Framework versions - Transformers 4.35.2 - Pytorch 2.1.0+cu118 - Datasets 2.15.0 - Tokenizers 0.15.0
MirageML/lowpoly-landscape	MirageML	"2023-05-05T20:53:06Z"	11	5	diffusers	[ "diffusers", "stable-diffusion", "text-to-image", "en", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	"2022-11-28T08:57:57Z"	--- language: - en tags: - stable-diffusion - text-to-image license: creativeml-openrail-m inference: true --- # Low Poly Landscape on Stable Diffusion via Dreambooth This the Stable Diffusion model fine-tuned the Low Poly Landscape concept taught to Stable Diffusion with Dreambooth. It can be used by modifying the `instance_prompt`: a photo of lowpoly_landscape # Run on [Mirage](https://app.mirageml.com) Run this model and explore text-to-3D on [Mirage](https://app.mirageml.com)! Here are is a sample output for this model: ![image 0](https://huggingface.co/MirageML/lowpoly-landscape/resolve/main/output.png) # Share your Results and Reach us on [Discord](https://discord.gg/9B2Pu2bEvj)! [![Discord Server](https://discord.com/api/guilds/1022387303022338058/widget.png?style=banner2)](https://discord.gg/9B2Pu2bEvj) [Image Source](https://www.deviantart.com/kautsar211086/art/Long-Time-No-See-457162094)
data-corentinv/bloom-fourthbrain-hackathon-1b7-lora-ads	data-corentinv	"2023-04-05T21:05:48Z"	4	0	transformers	[ "transformers", "bloom", "text-generation", "fourthbrain", "dtlb", "text2text-generation", "en", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text2text-generation	"2023-04-05T19:18:38Z"	--- license: mit pipeline_tag: text2text-generation language: - en metrics: - accuracy library_name: transformers tags: - fourthbrain - dtlb ---
stablediffusionapi/urpm-v13	stablediffusionapi	"2025-01-20T11:25:47Z"	20	6	diffusers	[ "diffusers", "stablediffusionapi.com", "stable-diffusion-api", "text-to-image", "ultra-realistic", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	"2023-07-18T02:50:34Z"	--- license: creativeml-openrail-m tags: - stablediffusionapi.com - stable-diffusion-api - text-to-image - ultra-realistic pinned: true --- # Uber Realistic Porn Merge V1.3 API Inference ![generated from modelslab.com](https://assets.modelslab.com/generations/d3d3f607-e8c6-4758-903a-17804fb4002b-0.png) ## Get API Key Get API key from [ModelsLab](https://modelslab.com/), No Payment needed. Replace Key in below code, change model_id to "urpm-v13" Coding in PHP/Node/Java etc? Have a look at docs for more code examples: [View docs](https://stablediffusionapi.com/docs) Try model for free: [Generate Images](https://stablediffusionapi.com/models/urpm-v13) Model link: [View model](https://stablediffusionapi.com/models/urpm-v13) Credits: [View credits](https://civitai.com/?query=Uber%20Realistic%20Porn%20Merge%20V1.3) View all models: [View Models](https://stablediffusionapi.com/models) import requests import json url = "https://stablediffusionapi.com/api/v4/dreambooth" payload = json.dumps({ "key": "your_api_key", "model_id": "urpm-v13", "prompt": "ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K", "negative_prompt": "painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime", "width": "512", "height": "512", "samples": "1", "num_inference_steps": "30", "safety_checker": "no", "enhance_prompt": "yes", "seed": None, "guidance_scale": 7.5, "multi_lingual": "no", "panorama": "no", "self_attention": "no", "upscale": "no", "embeddings": "embeddings_model_id", "lora": "lora_model_id", "webhook": None, "track_id": None }) headers = { 'Content-Type': 'application/json' } response = requests.request("POST", url, headers=headers, data=payload) print(response.text) > Use this coupon code to get 25% off DMGG0RBN

Subsets and Splits