Gaseg/llm-jp-3-13b-finetune

Uploaded model

• Developed by: Gaseg
• License: apache-2.0
• Finetuned from model : llm-jp/llm-jp-3-13b

Code

# python 3.10.12
!pip install -U pip
!pip install -U transformers
!pip install -U bitsandbytes
!pip install -U accelerate
!pip install -U datasets
!pip install -U peft
!pip install -U trl
!pip install -U wandb
!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。
from google.colab import userdata
HF_TOKEN = userdata.get('HF_TOKEN')
model_id = "llm-jp/llm-jp-3-13b"
adapter_id = "totsukash/llm-jp-3-13b-finetune"
# 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。
# （評価データセットのjsonlファイルのパスを設定してください）
datasets = []
with open("/content/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 = ""
# gemma
results = []
for data in tqdm(datasets):
    input = data["input"]
    prompt = f"""### 指示
    {input}
    ### 回答
    """
    
    # input_ids だけを取り出して使用
    input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(model.device)
    outputs = model.generate(input_ids, max_new_tokens=512, do_sample=False, repetition_penalty=1.2)
    output = tokenizer.decode(outputs[0][input_ids.size(1):], skip_special_tokens=True)
    
    results.append({"task_id": data["task_id"], "input": input, "output": output})
# # llmjp
# 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')