Update README.md

README.md

@@ -11,16 +11,66 @@ model-index:
   results: []
 language:
 - ja
+datasets:
+- Kendamarron/Magpie-Tanuki-8B-CoT
+- Kendamarron/OpenMathInstruct-2-ja-CoT
 ---
 
 <!-- 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
+# Model
 
-This model is a fine-tuned version of [llm-jp/llm-jp-3-3.7b-instruct](https://huggingface.co/llm-jp/llm-jp-3-3.7b-instruct) on the cot_normal and the cot_math datasets.
-It achieves the following results on the evaluation set:
-- Loss: 0.5311
+[llm-jp/llm-jp-3-3.7b-instruct](https://huggingface.co/llm-jp/llm-jp-3-3.7b-instruct)をCoTデータでファインチューニングすることで作成したreasoningモデルです。
+
+学習にはQwen2.5-32B-Instruct-AWQを使って生成した合成データセットを使用しています。.
+
+- [Kendamarron/llm-jp-3-3.7b-o1-v0.1](https://huggingface.co/datasets/Kendamarron/Magpie-Tanuki-8B-CoT)
+- [Kendamarron/OpenMathInstruct-2-ja-CoT](https://huggingface.co/datasets/Kendamarron/OpenMathInstruct-2-ja-CoT)
+
+## Usage
+```
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+device = "cuda"
+
+model = AutoModelForCausalLM.from_pretrained(
+    'Kendamarron/llm-jp-3-3.7b-o1-v0.1',
+    torch_dtype=torch.bfloat16,
+    device_map=device,
+)
+tokenizer = AutoTokenizer.from_pretrained('Kendamarron/Tokara-0.5B-Chat-dolly-jimba')
+
+messages = [
+  {"role": "system", "content": "あなたは優秀で論理的なアシスタントです。まずは<Thought></Thought>タグの中であなたの思考の過程を記載し、<Output></Output>タグの中に最終的にユーザーに提供する出力を記載します。"},
+  {"role": "user", "content": "1から10までの整数を足すと？"}
+]
+text = tokenizer.apply_chat_template(
+  messages,
+  tokenize=False,
+  add_generation_prompt=True
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(device)
+generated_ids = model.generate(
+  model_inputs.input_ids,
+  max_new_tokens=256,
+  do_sample=True,
+  top_p=0.95,
+  top_k=40,
+  temperature=0.7,
+  repetition_penalty=1.1,
+  pad_token_id=tokenizer.eos_token_id,
+  eos_token_id=tokenizer.eos_token_id,
+  no_repeat_ngram_size=2
+  )
+generated_ids = [
+  output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+]
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+
+print(response)
+```
 
 ## Model description