Model save

README.md

@@ -1,60 +1,58 @@
 ---
-library_name: peft
-license: gemma
 base_model: google/gemma-3-4b-pt
+library_name: transformers
+model_name: PROJECT_RUN_NAME
 tags:
-- base_model:adapter:google/gemma-3-4b-pt
-- lora
-- sft
-- transformers
+- generated_from_trainer
 - trl
-pipeline_tag: text-generation
-model-index:
-- name: PROJECT_RUN_NAME
-  results: []
+- sft
+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. -->
+# Model Card for PROJECT_RUN_NAME
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/colabear9806/law_ai2/runs/qtzznh01)
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/colabear9806/law_ai2/runs/qtzznh01)
-# PROJECT_RUN_NAME
+This model is a fine-tuned version of [google/gemma-3-4b-pt](https://huggingface.co/google/gemma-3-4b-pt).
+It has been trained using [TRL](https://github.com/huggingface/trl).
 
-This model is a fine-tuned version of [google/gemma-3-4b-pt](https://huggingface.co/google/gemma-3-4b-pt) on an unknown dataset.
+## Quick start
 
-## Model description
+```python
+from transformers import pipeline
 
-More information needed
+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="dlddu123/PROJECT_RUN_NAME", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
 
-## Intended uses & limitations
+## 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/colabear9806/law_ai2/runs/qtzznh01) 
 
-## Training and evaluation data
 
-More information needed
+This model was trained with SFT.
 
-## Training procedure
+### Framework versions
 
-### Training hyperparameters
+- TRL: 0.25.1
+- Transformers: 4.57.1
+- Pytorch: 2.9.0+cu126
+- Datasets: 4.0.0
+- Tokenizers: 0.22.1
+
+## Citations
 
-The following hyperparameters were used during training:
-- learning_rate: 0.0002
-- train_batch_size: 1
-- eval_batch_size: 8
-- seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 4
-- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: constant
-- lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 3
 
-### Framework versions
 
-- PEFT 0.18.0
-- Transformers 4.57.1
-- Pytorch 2.9.0+cu126
-- Datasets 4.0.0
-- Tokenizers 0.22.1
+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}}
+}
+```