# 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

base_model_id = "llm-jp/llm-jp-3-13b"  # モデルIDを設定。環境に合わせて変更
new_model_id = "my-finetuned-model"  # 学習後のモデル名を設定

bnb_config = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4", 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)

def find_all_linear_names(model):
    cls = torch.nn.Linear
    lora_module_names = set()
    for name, module in model.named_modules():
        if isinstance(module, cls):
            names = name.split('.')
            lora_module_names.add(names[0] if len(names) == 1 else names[-1])
    if 'lm_head' in lora_module_names:
        lora_module_names.remove('lm_head')
    return list(lora_module_names)

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)

dataset = load_dataset("json", data_files="path/to/your/instruction.json")  # データセットのパスを設定
prompt = """### 指示
{}
### 回答
{}"""
EOS_TOKEN = tokenizer.eos_token 
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 
    return { "formatted_text" : text, } 
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
)

training_arguments = TrainingArguments(
    output_dir=new_model_id,
    per_device_train_batch_size=1,
    gradient_accumulation_steps=2,
    optim="paged_adamw_32bit",
    num_train_epochs=5,
    logging_strategy="steps",
    logging_steps=10,
    warmup_steps=10,
    save_steps=100,
    save_total_limit = 2,
    max_steps = -1,
    learning_rate=5e-5,
    fp16=False,
    bf16=False,
    seed = 3407,
    group_by_length=True,
    report_to="none"
)

trainer = SFTTrainer(
    model=model,
    train_dataset=dataset["train"],
    peft_config=peft_config,
    max_seq_length=512,
    dataset_text_field="formatted_text",
    tokenizer=tokenizer,
    args=training_arguments,
    packing= False,
)
trainer.train()

import json
datasets = []
with open("path/to/your/tasks.jsonl", "r") as f: #jsonlファイルのパスを設定
    item = ""
    for line in f:
        line = line.strip()
        item += line
        if item.endswith("}"):
            datasets.append(json.loads(item))
            item = ""

results = []
for data in 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(".*/", "", new_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')