Kpitc5884/

kpitc5884-llm-jp-3-13b-finetune

!pip install unsloth  
!pip uninstall unsloth -y && pip install --upgrade --no-cache-dir "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"  
!pip install -U torch  
!pip install -U peft  

from unsloth import FastLanguageModel  
from peft import PeftModel  
import torch  
import json  
from tqdm import tqdm  
import re  

model_id = "llm-jp/llm-jp-3-13b" 
adapter_id = "Kpitc5884/kpitc5884-llm-jp-3-13b-finetune"  

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

model = AutoModelForCausalLM.from_pretrained(
    model_id,
    quantization_config=bnb_config,
    device_map="auto",
    token = HF_TOKEN        # ご自身のトークンをコピーしてください。
)
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True, token = HF_TOKEN)

datasets = []  
with open("タスクデータセット名", "r") as f:     # 任意のデータを読み込み（課題ではjsonl形式のファイルを使用）  
    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})