yokoe/llm-jp-3-13b-finetuned-tengentoppa-ds-wo-unsloth

How to use

import json
import os
from pathlib import Path

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


bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16,
)
model = AutoModelForCausalLM.from_pretrained(
    'llm-jp/llm-jp-3-13b',
    quantization_config=bnb_config,
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained(
    'llm-jp/llm-jp-3-13b',
    trust_remote_code=True,
)
model = PeftModel.from_pretrained(
    model,
    'yokoe/llm-jp-3-13b-finetuned-tengentoppa-ds-wo-unsloth',
)

# 推論対象データのロード
loaded_data = []
with open('./elyza-tasks-100-TV_0.jsonl', 'r') as f:
    item = ""
    for line in f:
      line = line.strip()
      item += line
      if item.endswith("}"):
        loaded_data.append(json.loads(item))
        item = ""

# 推論
results = []
for i, data in enumerate(tqdm(loaded_data)):

    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=1024,
          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})

with open('./elyza-tasks-100-TV_0_preds.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')