Model save

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,59 +1,58 @@
 ---
-base_model: meta-llama/Meta-Llama-3-8B
-library_name: peft
-license: llama3
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+library_name: transformers
+model_name: sft-llama-cloud
 tags:
-- trl
-- sft
 - generated_from_trainer
-model-index:
-- name: sft-llama-cloud
-  results: []
+- sft
+- trl
+licence: license
 ---
 
-<!-- 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. -->
-
-# sft-llama-cloud
+# Model Card for sft-llama-cloud
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.5621
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
 
-## Model description
+## Quick start
 
-More information needed
+```python
+from transformers import pipeline
 
-## Intended uses & limitations
+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="Bakugo123/sft-llama-cloud", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
 
-More information needed
-
-## Training and evaluation data
+## Training procedure
 
-More information needed
+[<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/axiler/sft_llama3-8b-cloud-fine-tune/runs/d6fizy5q) 
 
-## Training procedure
 
-### Training hyperparameters
+This model was trained with SFT.
 
-The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 1
-- eval_batch_size: 8
-- seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- num_epochs: 5
-- mixed_precision_training: Native AMP
+### Framework versions
 
-### Training results
+- TRL: 0.19.1
+- Transformers: 4.53.1
+- Pytorch: 2.7.1
+- Datasets: 2.16.0
+- Tokenizers: 0.21.2
 
+## Citations
 
 
-### Framework versions
 
-- PEFT 0.12.0
-- Transformers 4.43.4
-- Pytorch 2.4.0a0+07cecf4168.nv24.05
-- Datasets 2.20.0
-- Tokenizers 0.19.1
+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 Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -3,6 +3,9 @@
   "auto_mapping": null,
   "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
   "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -11,19 +14,23 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 16,
+  "lora_bias": false,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
+  "qalora_group_size": 16,
   "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
   "use_dora": false,
+  "use_qalora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:461efed3c23271fd56410c7ca7b80996fbd31b52647b85f8638c42a6f040b596
+oid sha256:85df9188028a207e0e8a012c9eeff4eea55795f46fdf9214629db4544e05bac1
 size 109069176

chat_template.jinja

@@ -0,0 +1,5 @@
+{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
+
+'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
+
+' }}{% endif %}

special_tokens_map.json

@@ -12,6 +12,5 @@
     "normalized": false,
     "rstrip": false,
     "single_word": false
-  },
-  "pad_token": "<|eot_id|>"
+  }
 }

tokenizer_config.json

@@ -2050,14 +2050,13 @@
     }
   },
   "bos_token": "<|begin_of_text|>",
-  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<|eot_id|>",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6286358a7fc536d696b60de46cef40fc148ae6d8dce5a985a9af09700228159
-size 5496
+oid sha256:1c637cb65aafc76e8d7b3ffd129a81b98216f29c4265d8c6ee3f95985ce2fc31
+size 6161