komatsurui/llm-jp-3-13b-it_lora

Uploaded model

• Developed by: komatsurui
• 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.

データセットの読み込み

"""python

import json datasets = [] with open("/content/drive/MyDrive/LLM_final_competition/elyza-tasks-100-TV_0.jsonl", "r") as f: item = "" for line in f: line = line.strip() item += line if item.endswith("}"): datasets.append(json.loads(item)) item = ""

推論実行

"""python

from tqdm import tqdm

FastLanguageModel.for_inference(model)

results = [] for dt in tqdm(datasets): 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": dt["task_id"], "input": input, "output": prediction})

結果の保存

"""python

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