Training in progress, step 100

README.md

@@ -1,22 +1,69 @@
 ---
 base_model: unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit
+library_name: transformers
+model_name: HidatoQwenModel
 tags:
-- text-generation-inference
-- transformers
-- unsloth
-- qwen2
+- generated_from_trainer
+- grpo
 - trl
-license: apache-2.0
-language:
-- en
+- unsloth
+licence: license
 ---
 
-# Uploaded  model
+# Model Card for HidatoQwenModel
+
+This model is a fine-tuned version of [unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit](https://huggingface.co/unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit).
+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="michlea/HidatoQwenModel", 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/michlea-hse-spb/huggingface/runs/m65yzfna) 
+
+
+This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
+
+### Framework versions
+
+- TRL: 0.23.0
+- Transformers: 4.55.4
+- Pytorch: 2.7.1
+- Datasets: 3.6.0
+- Tokenizers: 0.21.4
+
+## Citations
+
+Cite GRPO as:
 
-- **Developed by:** michlea
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit
+```bibtex
+@article{shao2024deepseekmath,
+    title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
+    author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
+    year         = 2024,
+    eprint       = {arXiv:2402.03300},
+}
 
-This qwen2 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)
+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

@@ -25,13 +25,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
+    "gate_proj",
     "down_proj",
-    "up_proj",
-    "o_proj",
-    "v_proj",
     "k_proj",
-    "q_proj",
-    "gate_proj"
+    "o_proj",
+    "up_proj",
+    "v_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:527d0c067274c84ccf2c65b6b7639e7d3f4a6595a6b57e47519521dfd3b6a1ff
+oid sha256:6c7c39d277354d47f1a92038c07c003f26416ccff295aeb12f614d1876f2f0a8
 size 479005064

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:988c8002f08927e1ff0bcd03c404e65e0ea558a393fe5b18457b2b40d64758dc
+size 7249