Model Card for Model ID

Model Details

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

Developed by: [More Information Needed]
Funded by [optional]: [More Information Needed]
Shared by [optional]: [More Information Needed]
Model type: LoRA adapter
Language(s) (NLP): JA
License: LLAMA 3.1 COMMUNITY LICENSE
Finetuned from model [optional]: llm-jp/llm-jp-3-13b

Model Sources [optional]

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

Uses

Jupyter Notebook

ライブラリの準備

!pip install -U transformers peft safetensors bitsandbytes

Hugging Faceのアダプターリポジトリを使う Hugging Face Hub上のリポジトリにあるアダプターを直接読み込むコードは以下のようになります。

from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
from peft import PeftModel
import torch

# ベースモデル名とアダプターのリポジトリ名
base_model_name = "llm-jp/llm-jp-3-13b"  # 事前学習済みモデル
revision = "cd3823f4c1fcbb0ad2e2af46036ab1b0ca13192a"
adapter_repo_id = "Eito2002/llm-jp-3-13b-finetune"

# QLoRAの設定
bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16,
)

# トークナイザーとベースモデルを読み込み
tokenizer = AutoTokenizer.from_pretrained(base_model_name, revision=revision)
base_model = AutoModelForCausalLM.from_pretrained(base_model_name, revision=revision, quantization_config=bnb_config, device_map="auto")

# Hugging Faceからアダプターを読み込み
model = PeftModel.from_pretrained(base_model, adapter_repo_id)

# モデルの確認
print("アダプターが統合されました！")
print(model)

推論を実行統合したモデルを使って推論を行います。

# 推論テキスト
prompt = "AIとは何ですか？"

# トークナイズ
tokenized_input = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt").to(model.device)
attention_mask = torch.ones_like(tokenized_input)

# 推論を実行
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)

print(output)

アダプター統合の確認アダプターが正しく統合されたかどうかは、パラメータの統計情報を見ることで確認できます。

model.print_trainable_parameters()

elyza-tasks-100-TV_0.jsonlを入力として用いる方法、データ読み取り

import json

datasets = []
with open("./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 = ""

jsonlファイルへの出力

from tqdm import tqdm

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"], "input": input, "output": output})

with open(f"./elyza-tasks-100-TV-outputs.jsonl", 'w', encoding='utf-8') as f:
    for result in results:
        json.dump(result, f, ensure_ascii=False)  # ensure_ascii=False for handling non-ASCII characters
        f.write('\n')

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.

[More Information Needed]

Training Details

Training Data

[More Information Needed]

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]