Update README.md

README.md

@@ -46,17 +46,81 @@ model = AutoModelForCausalLM.from_pretrained(
 tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True, token=HF_TOKEN)
 ```
 
-### Output Format
+### Output Generation and Format
 
-The model outputs results in JSONL format with required fields:
-- task_id: Task identifier
-- output: Generated response
+#### Implementation Details
 
-Example output:
+To generate output in the required JSONL format:
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
+from peft import PeftModel
+import torch
+from tqdm import tqdm
+import json
+
+# Load model and tokenizer
+model_id = "yuhkis/llm-jp-3-13b-finetune"
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_compute_dtype=torch.bfloat16,
+)
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    quantization_config=bnb_config,
+    device_map="auto",
+    token=HF_TOKEN
+)
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True, token=HF_TOKEN)
+
+# Generate outputs
+results = []
+for data in tqdm(datasets):
+    input = data["input"]
+    prompt = f"""### 指示
+    {input}
+    ### 回答
+    """
+    
+    tokenized_input = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt").to(model.device)
+    attention_mask = torch.ones_like(tokenized_input)
+    
+    with torch.no_grad():
+        outputs = model.generate(
+            tokenized_input,
+            attention_mask=attention_mask,
+            max_new_tokens=100,
+            do_sample=False,
+            repetition_penalty=1.2,
+            pad_token_id=tokenizer.eos_token_id
+        )[0]
+    output = tokenizer.decode(outputs[tokenized_input.size(1):], skip_special_tokens=True)
+    
+    results.append({"task_id": data["task_id"], "output": output})
+
+# Save results to JSONL file
+with open("results.jsonl", 'w', encoding='utf-8') as f:
+    for result in results:
+        json.dump(result, f, ensure_ascii=False)
+        f.write('\n')
+```
+
+#### Output Format Specification
+
+Required fields in the JSONL output:
+- task_id: Task identifier (integer)
+- output: Generated response (string)
+
+Example output format:
 ```json
 {"task_id": 0, "output": "応答テキスト"}
 ```
 
+Note: While additional fields (e.g., input, eval_aspect) may be included, only task_id and output are required for submission.
+```
+
 ### Out-of-Scope Use
 
 This model should not be used for: