Stable Diffusion Community (Unofficial, Non-profit)

community

AI & ML interests

Enhance and upgrade SD-models

sd-community's activity

AtAndDev 
posted an update 2 days ago
view post
Post
501
Sup yall
Just finished finetuned gemma 3 12b and 27b with a custom rl-like orm for a half-subjective task (rating food and cosmetic products health based on some personal info), tho I want to serve it with a pay-per-token inference engine, does anyone know a platform to host? Btw, as of my knowledge together and some others support lora with a limited list of base models (which do not have gemma 3) so...

More info about that app coming soon :)
We are prepearing to launch...
Stay tooned.
This is getting too long.
See ya
AtAndDev 
posted an update 7 days ago
view post
Post
4065
There seems to multiple paid apps shared here that are based on models on hf, but some ppl sell their wrappers as "products" and promote them here. For a long time, hf was the best and only platform to do oss model stuff but with the recent AI website builders anyone can create a product (really crappy ones btw) and try to sell it with no contribution to oss stuff. Please dont do this, or try finetuning the models you use...
Sorry for filling yall feed with this bs but yk...
  • 5 replies
·
AtAndDev 
posted an update 10 days ago
view post
Post
1535
Gemma 3 seems to be really good at human preference. Just waiting for ppl to see it.
not-lain 
posted an update 11 days ago
ehristoforu 
posted an update 27 days ago
view post
Post
2821
Introducing our first standalone model – FluentlyLM Prinum

Introducing the first standalone model from Project Fluently LM! We worked on it for several months, used different approaches and eventually found the optimal one.

General characteristics:
- Model type: Causal language models (QwenForCausalLM, LM Transformer)
- Number of parameters: 32.5B
- Number of parameters (not embedded): 31.0B
- Number of layers: 64
- Context: 131,072 tokens
- Language(s) (NLP): English, French, Spanish, Russian, Chinese, Japanese, Persian (officially supported)
- License: MIT

Creation strategy:
The basis of the strategy is shown in Pic. 2.
We used Axolotl & Unsloth for SFT-finetuning with PEFT LoRA (rank=64, alpha=64) and Mergekit for SLERP and TIES mergers.

Evolution:
🏆 12th place in the Open LLM Leaderboard ( open-llm-leaderboard/open_llm_leaderboard) (21.02.2025)

Detailed results and comparisons are presented in Pic. 3.

Links:
- Model: fluently-lm/FluentlyLM-Prinum
- GGUF version: mradermacher/FluentlyLM-Prinum-GGUF
- Demo on ZeroGPU: ehristoforu/FluentlyLM-Prinum-demo
  • 7 replies
·
AtAndDev 
posted an update about 1 month ago
ameerazam08 
posted an update about 2 months ago
not-lain 
posted an update about 2 months ago
AtAndDev 
posted an update about 2 months ago
view post
Post
1896
everywhere i go i see his face
AtAndDev 
posted an update about 2 months ago
view post
Post
537
Deepseek gang on fire fr fr
AtAndDev 
posted an update 2 months ago
view post
Post
1617
R1 is out! And with a lot of other R1 releated models...
not-lain 
posted an update 2 months ago
view post
Post
1671
we now have more than 2000 public AI models using ModelHubMixin🤗
not-lain 
posted an update 2 months ago
view post
Post
4041
Published a new blogpost 📖
In this blogpost I have gone through the transformers' architecture emphasizing how shapes propagate throughout each layer.
🔗 https://huggingface.co/blog/not-lain/tensor-dims
some interesting takeaways :
1aurent 
posted an update 3 months ago
ehristoforu 
posted an update 3 months ago
view post
Post
3678
✒️ Ultraset - all-in-one dataset for SFT training in Alpaca format.
fluently-sets/ultraset

❓ Ultraset is a comprehensive dataset for training Large Language Models (LLMs) using the SFT (instruction-based Fine-Tuning) method. This dataset consists of over 785 thousand entries in eight languages, including English, Russian, French, Italian, Spanish, German, Chinese, and Korean.

🤯 Ultraset solves the problem faced by users when selecting an appropriate dataset for LLM training. It combines various types of data required to enhance the model's skills in areas such as text writing and editing, mathematics, coding, biology, medicine, finance, and multilingualism.

🤗 For effective use of the dataset, it is recommended to utilize only the "instruction," "input," and "output" columns and train the model for 1-3 epochs. The dataset does not include DPO or Instruct data, making it suitable for training various types of LLM models.

❇️ Ultraset is an excellent tool to improve your language model's skills in diverse knowledge areas.
AtAndDev 
posted an update 3 months ago
view post
Post
465
@s3nh Hey man check your discord! Got some news.
  • 4 replies
·
not-lain 
posted an update 4 months ago
view post
Post
2347
ever wondered how you can make an API call to a visual-question-answering model without sending an image url 👀

you can do that by converting your local image to base64 and sending it to the API.

recently I made some changes to my library "loadimg" that allows you to make converting images to base64 a breeze.
🔗 https://github.com/not-lain/loadimg

API request example 🛠️:
from loadimg import load_img
from huggingface_hub import InferenceClient

# or load a local image
my_b64_img = load_img(imgPath_url_pillow_or_numpy ,output_type="base64" ) 

client = InferenceClient(api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx")

messages = [
	{
		"role": "user",
		"content": [
			{
				"type": "text",
				"text": "Describe this image in one sentence."
			},
			{
				"type": "image_url",
				"image_url": {
					"url": my_b64_img # base64 allows using images without uploading them to the web
				}
			}
		]
	}
]

stream = client.chat.completions.create(
    model="meta-llama/Llama-3.2-11B-Vision-Instruct", 
	messages=messages, 
	max_tokens=500,
	stream=True
)

for chunk in stream:
    print(chunk.choices[0].delta.content, end="")