Himalayan-wildcat/llm-jp-3-13b-finetune

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

• Developed by: Hiroaki Hara(@Himalayan-wildcat)
• Language(s) (NLP): ja
• License: MIT
• Finetuned from model [optional]: llm-jp/llm-jp-3-13b

Uses

import json
import re

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


model_id = "hiroakihara/llm-jp-3-13b-finetune"
hf_token = "YOUR HUGGINGFACE TOKEN"
test_jsonl_data = "elyza-tasks-100-TV_0.jsonl"

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)

tokenizer = AutoTokenizer.from_pretrained(
    model_id, 
    trust_remote_code=True, 
    token=hf_token)

datasets = []
with open(test_jsonl_data) 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})        

jsonl_id = re.sub(".*/", "", model_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)
        f.write('\n')