README.md

metadata

library_name: transformers
license: cc-by-4.0
datasets:
  - elyza/ELYZA-tasks-100
language:
  - ja
base_model:
  - llm-jp/llm-jp-3-13b

Uses

以下のコードで40分ほどでElyza-tasks-TV-100の推論が終了します。

#推論時のコード

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

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

# Hugging Faceで取得したTokenをこちらに貼る。
HF_TOKEN = "YOUR_HF_TOKEN"  

model_id = "llm-jp/llm-jp-3-13b"  
adapter_id = "kiseich/llm-jp-3-13b-Etask"  

# 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)  
model.eval()  

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 = ""  


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})  

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')  
        
#以上でjsonlファイルを得る。  

Training Data

Elyza-tasks-100にてSFTされている。