onhrs/ono-llm-jp-3-13b-finetune

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: [More Information Needed]
• Language(s) (NLP): [More Information Needed]
• License: [More Information Needed]
• 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

!pip install -U bitsandbytes
!pip install -U transformers
!pip install -U accelerate
!pip install -U datasets
!pip install -U peft


from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
    BitsAndBytesConfig,
)
from peft import PeftModel
import torch
from tqdm import tqdm
import json

# 必要なライブラリを読み込み
from peft import PeftModel
import torch
import json
from tqdm import tqdm
import re

## ベースとなるモデルと学習したLoRAのアダプタ
model_id = "llm-jp/llm-jp-3-13b"
adapter_id = "onhrs/ono-llm-jp-3-13b-finetune"

## Hugging Face Token を指定
HF_TOKEN = "..."


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

# Load model
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    quantization_config=bnb_config,
    device_map="auto",
    token = HF_TOKEN
)

# Load tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True, token = HF_TOKEN)

# 元のモデルにLoRAのアダプタを統合。
model = PeftModel.from_pretrained(model, adapter_id, token = HF_TOKEN)


# データセットの読み込み。
# omnicampusの開発環境では、左にタスクのjsonlをドラッグアンドドロップしてから実行。
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 = ""




# llmjp
results = []
for data in tqdm(datasets):
    input = data["input"]
    
    prompt = f"""### 指示
    {input}
    ### 回答
    """
    
    # トークナイズ処理を修正
    inputs = tokenizer(
        prompt,
        return_tensors="pt",
        add_special_tokens=False
    ).to(model.device)
    
    # generateの呼び出し
    with torch.no_grad():
        outputs = model.generate(
            input_ids=inputs.input_ids,  # input_idsを明示的に指定
            attention_mask=inputs.attention_mask,  # tokenizerから取得したattention_maskを使用
            max_new_tokens=100,
            do_sample=False,
            repetition_penalty=1.2,
            pad_token_id=tokenizer.eos_token_id
        )[0]
    
    # 出力のデコード
    output = tokenizer.decode(outputs[inputs.input_ids.size(1):], skip_special_tokens=True)
    
    # 結果の保存
    results.append({
        "task_id": data["task_id"], 
        "input": input, 
        "output": output
    })

#結果の出力
import re
jsonl_id = re.sub(".*/", "", adapter_id)
with open(f"./{jsonl_id}-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')

学習データセット

Language	Dataset	詳細
Japanese	elyza/ELYZA-tasks-100	https://huggingface.co/datasets/elyza/ELYZA-tasks-100
Japanese	ELYZA-tasks-100からTanuki-8x8Bで合成データ生成	https://zenn.dev/karaage0703/articles/e79a1db743b8e4
Japanese	ichikara-instruction	https://liat-aip.sakura.ne.jp/wp/llmのための日本語インストラクションデータ作成/llmのための日本語インストラクションデータ-公開/
Japanese	ichikara-instructionからTanuki-8x8Bで合成データ生成