IchiShira/llm-jp-3-13b-finetune-2

Uploaded model

• Developed by: IchiShira
• License: apache-2.0
• Finetuned from model : llm-jp/llm-jp-3-13b

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

出力方法

""" python """

from tqdm import tqdm

推論

results = [] for dt in tqdm(data): input = dt["input"]

prompt = f"""### 指示\n{input}\n### 回答\n"""

inputs = tokenizer([prompt], return_tensors = "pt").to(model.device)

outputs = model.generate(**inputs, max_new_tokens = 512, use_cache = True, do_sample=False, repetition_penalty=1.2) prediction = tokenizer.decode(outputs[0], skip_special_tokens=True).split('\n### 回答')[-1]

results.append({"task_id": data["task_id"], "input": input, "output": output})

with open(f"/content/{model_name}_output.jsonl", 'w', encoding='utf-8') as f: for result in results: json.dump(result, f, ensure_ascii=False) f.write('\n')

"""