Update README.md

README.md

@@ -62,7 +62,6 @@ import os
 os.environ["HF_TOKEN"] = "あなたのHugging Faceトークン"
 
 from vllm.lora.request import LoRARequest
-
 llm = vllm.LLM(
     MODEL_NAME, # "deepseek-ai/deepseek-math-7b-instruct"
     tensor_parallel_size=1, # 2, 4
@@ -79,15 +78,56 @@ llm = vllm.LLM(
 )
 tokenizer = llm.get_tokenizer()
 
+from transformers import AutoTokenizer
+sft_tokenizer = AutoTokenizer.from_pretrained(
+    "weblab-GENIAC/Tanuki-8B-dpo-v1.0"
+)
+tokenizer.chat_template = sft_tokenizer.chat_template
+
+from huggingface_hub import snapshot_download
+lora_path = snapshot_download(repo_id="OsakanaTeishoku/1204lora")
+
+from datasets import load_dataset
+# jsonlファイルのパスを指定します。
+data_files = {"test": "elyza-tasks-100-TV_0.jsonl"}  # "your_jsonl_file.jsonl" を実際のファイル名に置き換えてください
+# load_dataset関数を使用してデータを読み込みます。
+tasks = load_dataset("json", data_files=data_files, split="test")
+# データセットを確認します。
+
+messages_list = [
+    [{"role": "user", "content": tasks["input"][i]}] for i in range(len(tasks))
+]
+prompts = [line[0]["content"] for line in messages_list]
+prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
+sampling_params = vllm.SamplingParams(
+    temperature=1.5,
+    max_tokens=1024,
+    repetition_penalty=1.05,
+    min_p=0.1,
+)
+outputs = llm.generate(
+    prompt_token_ids=prompt_token_ids,
+    sampling_params=sampling_params,
+    lora_request=LoRARequest("lora", 1, lora_path), # LoRA adapter
+)
+for prompt, response in zip(prompts, outputs):
+    print("prompt:", prompt)
+    print("output:", response.outputs[0].text.strip())
+    print("-"*80)   
+import json
+data = [{
+    "task_id": i, 
+    #"input": prompts[i],
+    "output": outputs[i].outputs[0].text.strip()
+} for i in range(len(tasks))]
+file_path_with_unicode = 'output.jsonl'
+with open(file_path_with_unicode, 'w', encoding='utf-8') as file:
+    for entry in data:
+        json.dump(entry, file, ensure_ascii=False)
+        file.write('\n')
+print(f"Saved json {file_path_with_unicode} !")
 ```
 
-
-
-
-
-
-
-
 # Uploaded  model
 
 - **Developed by:** OsakanaTeishoku