以下、推論用のコードになります。

!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

model_id = "sarashi0811/llm2024_v3"

# 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"
)

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

# 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 = ""

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(".*/", "", "check")
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')

Base model