sallm/llm-jp-3-13b-finetune14

# python 3.10.12
!pip install -U pip
!pip install -U transformers
!pip install -U bitsandbytes
!pip install -U accelerate
!pip install -U datasets
!pip install -U peft
!pip install -U trl
!pip install -U wandb
!pip install ipywidgets --upgrade

from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
    BitsAndBytesConfig,
    TrainingArguments,
    logging,
)
from peft import (
    LoraConfig,
    PeftModel,
    get_peft_model,
)
import os, torch, gc
from datasets import load_dataset
import bitsandbytes as bnb
from trl import SFTTrainer

# Hugging Face Token
HF_TOKEN = ""

base_model_id = "models/models--llm-jp--llm-jp-3-13b/snapshots/cd3823f4c1fcbb0ad2e2af46036ab1b0ca13192a" #Fine-Tuningするベースモデル
# omnicampus以外の環境をご利用の方は以下をご利用ください。
# base_model_id = "llm-jp/llm-jp-3-13b" 
new_model_id = "llm-jp-3-13b-finetune14" #Fine-Tuningしたモデルにつけたい名前

bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4", # nf4は通常のINT4より精度が高く、ニューラルネットワークの分布に最適です
    bnb_4bit_compute_dtype=torch.bfloat16,
)

model = AutoModelForCausalLM.from_pretrained(
    base_model_id,
    quantization_config=bnb_config,
    device_map="auto"
)

tokenizer = AutoTokenizer.from_pretrained(base_model_id, trust_remote_code=True)


def find_all_linear_names(model):
    cls = bnb.nn.Linear4bit # 4bit量子化線形層クラスを指定
    lora_module_names = set() # ここに取得した線形層を保持します。

    # モデル内の全てのモジュールを探索します
    for name, module in model.named_modules():
        if isinstance(module, cls): # モジュールが4bit量子化線形層の場合
            names = name.split('.') # モジュールの名前を分割 (ネストされてる際などに対処)
            lora_module_names.add(names[0] if len(names) == 1 else names[-1]) # 最下層の名前をlora_module_namesに追加

    # 'lm_head' は16ビット演算の際に除外する必要があるため、lora_module_namesから削除
    if 'lm_head' in lora_module_names:
        lora_module_names.remove('lm_head')

    return list(lora_module_names) # lora_module_namesをリストに変換して返します。

modules = find_all_linear_names(model)

peft_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
    target_modules=modules,
)

model = get_peft_model(model, peft_config)

file_paths = [
    "./ichikara-instruction-003-001-1.json",
    "./zero_xx_0000_4.json"
]

dataset = load_dataset("json", data_files=file_paths)

# 学習時のプロンプトフォーマットの定義
prompt = """### 指示
{}
### 回答
{}"""


"""
formatting_prompts_func: 各データをプロンプトに合わせた形式に合わせる
"""
EOS_TOKEN = tokenizer.eos_token # トークナイザーのEOSトークン（文末トークン）
def formatting_prompts_func(examples):
    input = examples["text"] # 入力データ
    output = examples["output"] # 出力データ
    text = prompt.format(input, output) + EOS_TOKEN # プロンプトの作成
    return { "formatted_text" : text, } # 新しいフィールド "formatted_text" を返す
pass

# # 各データにフォーマットを適用
dataset = dataset.map(
    formatting_prompts_func,
    num_proc= 4, # 並列処理数を指定
)

dataset

# データを確認
print(dataset["train"]["formatted_text"][3])

training_arguments = TrainingArguments(
    output_dir=new_model_id,
    per_device_train_batch_size=1,
    gradient_accumulation_steps=2,
    optim="adamw_hf",
    num_train_epochs=1,
    logging_strategy="steps",
    logging_steps=10,
    warmup_steps=10,
    save_steps=100,
    save_total_limit = 2,
    max_steps = -1,
    learning_rate=5e-5,
    fp16=True,
    bf16=False,
    seed = 3407,
    group_by_length=True,
    report_to="none"
)

ds_elyza = load_dataset("elyza/ELYZA-tasks-100")

def formatting_prompts_func_elyza(examples):
    input = examples["input"] # 入力データ
    output = examples["output"] # 出力データ
    text = prompt.format(input, output) + EOS_TOKEN # プロンプトの作成
    return { "formatted_text" : text, } # 新しいフィールド "formatted_text" を返す
pass

# # 各データにフォーマットを適用
ds_elyza = ds_elyza.map(
    formatting_prompts_func_elyza,
    num_proc= 4, # 並列処理数を指定
)
from datasets import concatenate_datasets
ds_elyza["train"]=ds_elyza["test"]
ds_combined = concatenate_datasets([ds_elyza["train"],dataset["train"]])

trainer = SFTTrainer(
    model=model,
    train_dataset=ds_combined,
    peft_config=peft_config,
    max_seq_length= 1536,
    dataset_text_field="formatted_text",
    tokenizer=tokenizer,
    args=training_arguments,
    packing= False,
)

model.config.use_cache = False # キャッシュ機能を無効化
trainer.train() # トレーニングを実行

# 
max_new_tokens = 1000
repetition_penalty =1.194
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 = ""
        

# 推論。

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=max_new_tokens,
          do_sample=False,
          repetition_penalty=repetition_penalty,
          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})


# こちらで生成されたjsolを提出してください。
# 本コードではinputとeval_aspectも含んでいますが、なくても問題ありません。
# 必須なのはtask_idとoutputとなります。
jsonl_id = re.sub(".*/", "", new_model_id)
with open(f"./{jsonl_id}-{max_new_tokens}_{repetition_penalty}_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')
print(repetition_penalty)

Model Card for Model ID

Model Details

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: [More Information Needed]
• Funded by [optional]: [More Information Needed]
• Shared by [optional]: [More Information Needed]
• Model type: [More Information Needed]
• Language(s) (NLP): [More Information Needed]
• License: [More Information Needed]
• Finetuned from model [optional]: [More Information Needed]

Model Sources [optional]

• Repository: [More Information Needed]
• Paper [optional]: [More Information Needed]
• Demo [optional]: [More Information Needed]

Uses

Direct Use

[More Information Needed]

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

[More Information Needed]

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

• Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

• Hardware Type: [More Information Needed]
• Hours used: [More Information Needed]
• Cloud Provider: [More Information Needed]
• Compute Region: [More Information Needed]
• Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]