Hugging Face's logo

n4
/
llm-jp-3-13b-finetune-10

PEFT
Safetensors
Model card Files Community
llm-jp-3-13b-finetune-10 / README.md
n4's picture
n4
Upload fine-tuned model
f83738c
preview code
|
raw
history blame contribute delete
8.49 kB
metadata
base_model: llm-jp/llm-jp-3-13b
library_name: peft

Model Card for Model ID

Model Details

Model Description

  • Developed by: [More Information Needed]
  • Funded by [optional]: [More Information Needed]
  • Shared by [optional]: [More Information Needed]
  • Model type: [More Information Needed]
  • Language(s) (NLP): [More Information Needed]
  • License: 本モデルは、CC-BY-NC-SAライセンス下で利用可能なデータセットを用いて学習されています。そのため、本モデルを利用する際には、元データセットのライセンスに準拠する必要があります。
  • Finetuned from model [optional]: [More Information Needed]

Model Sources [optional]

  • Repository: [More Information Needed]
  • Paper [optional]: [More Information Needed]
  • Demo [optional]: [More Information Needed]

Uses

Direct Use

[More Information Needed]

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

Google Colabで実行してください。

!pip install bitsandbytes

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
import json
from tqdm import tqdm

# 必要な設定
model_name = "n4/llm-jp-3-13b-finetune-10"
max_seq_length = 1024
load_in_4bit = True  # 4-bit量子化を有効化

# モデルとトークナイザーのロード
print("モデルをロード中...")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
dtype = torch.float16 if load_in_4bit else None

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    device_map="auto",
    torch_dtype=dtype,
    load_in_4bit=load_in_4bit,
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
print("モデルのロードが完了しました。")

# 推論用ファイルの用意
elyza-tasks-100-TV_0.jsonl を /content/elyza-tasks-100-TV_0.jsonl となるようにアップロードしておいてください。


# データセットの読み込み
datasets = []
with open("./elyza-tasks-100-TV_0.jsonl", "r") as f:
    item = ""
    for i, line in enumerate(f):
        line = line.strip()
        item += line
        if item.endswith("}"):
            data = json.loads(item)
            # task_id がない場合は行番号を追加
            if "task_id" not in data:
                data["task_id"] = i  # 0から始まる行番号
            datasets.append(data)
            item = ""

# 推論
results = []
print("推論を開始します...")
for dt in tqdm(datasets):
    input_text = dt["input"]

    # プロンプト作成
    prompt = f"<s>指示を読んで、質問内容を把握してください。把握した内容を回答してください。選択肢の並べ変えや、意味の理解など、多様な質問が想定されるので質問を注意深くみてください。</s><s>### 指示\n{input_text}\n\n\n### 回答\n"

    # トークナイズ（token_type_idsを削除）
    inputs = tokenizer(prompt, return_tensors="pt").to(device)
    inputs.pop("token_type_ids", None)  # 不要なキーを削除

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

    # 結果を保存
    results.append({"task_id": dt["task_id"], "input": input_text, "output": prediction})

# 推論結果の保存
output_file = f"{model_name.replace('/', '_')}_output.jsonl"
with open(output_file, "w") as f:
    for result in results:
        f.write(json.dumps(result, ensure_ascii=False) + "\n")

print(f"推論が完了しました。結果は {output_file} に保存されました。")

Training Details

Training Data

  • 本モデルは、CC-BY-NC-SAライセンス下で提供されているデータセットを用いて学習されています。
    このライセンスは、非営利的利用及び同一条件での共有を求めるため、利用者はライセンス条件を必ず確認してください。
    参照: CC-BY-NC-SA ライセンス詳細

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

  • Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

  • Hardware Type: [More Information Needed]
  • Hours used: [More Information Needed]
  • Cloud Provider: [More Information Needed]
  • Compute Region: [More Information Needed]
  • Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]

Framework versions

  • PEFT 0.13.2