---
base_model: llm-jp/llm-jp-3-13b
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: apache-2.0
language:
- en
---

# Uploaded  model

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

This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.

[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)




# sample of use(python)

from transformers import (


    AutoModelForCausalLM,

    AutoTokenizer,

    BitsAndBytesConfig,

)

## モデルのロード
import torch
from tqdm import tqdm
import json


HF_TOKEN = "Hugging Face Token"　#Hugging Face のAPIキーを入力（read)

model_name = "satoyutaka/llm-jp-3-13b-ftELZ-2"　#作成したモデル名


## 量子化パラメータの設定


bnb_config = BitsAndBytesConfig(

    load_in_4bit=True,

    bnb_4bit_quant_type="nf4",

    bnb_4bit_compute_dtype=torch.bfloat16,

    bnb_4bit_use_double_quant=False,
)


## 問題文の読み込み

datasets = []


with open("elyza-tasks-100-TV_0.jsonl", "r") as f:　#ファイルを格納したパスに書き換えてください。

    item = ""

    for line in f:

      line = line.strip()

      item += line

      if item.endswith("}"):

        datasets.append(json.loads(item))

        item = ""

results = []



## 推論


from tqdm import tqdm


results = []


for dt in tqdm(datasets):


  input = dt["input"]


  prompt = f"""### 指示\n{input}\n### 回答\n"""


  inputs = tokenizer([prompt], return_tensors = "pt").to(model.device)

  
  outputs = model.generate(**inputs, max_new_tokens = 512, use_cache = True, do_sample=False, repetition_penalty=1.2)

  
  prediction = tokenizer.decode(outputs[0], skip_special_tokens=True).split('\n### 回答')[-1]


  results.append({"task_id": dt["task_id"], "input": input, "output": prediction})


## 提出ファイルの作成


import re


model_name = re.sub(".*/", "", model_name)


with open(f"./{model_name}-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')