File size: 11,244 Bytes
768d3d4 1bc814c 768d3d4 1bc814c e5a3930 768d3d4 1bc814c 768d3d4 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 6d177b0 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b f4b0c9b b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b 772dd33 b8c1d8b fbfe906 b8c1d8b fbfe906 b8c1d8b fbfe906 b8c1d8b fbfe906 b8c1d8b fbfe906 b8c1d8b fbfe906 6acdb89 b8c1d8b b81eee6 b8c1d8b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 |
---
base_model: llm-jp/llm-jp-3-13b
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: cc-by-nc-4.0
language:
- ja
datasets:
- DeL-TaiseiOzaki/Tengentoppa-sft-v1.0
---
# Uploaded model
- **Developed by:** daichira
- **License:** cc-by-nc-4.0
- **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)
### README.md
# llm-jp-3-13b-itnew9
## 概要
このプロジェクトは、Hugging Face上で提供される言語モデル`llm-jp/llm-jp-3-13b`を基盤とし、さらなる指示応答タスク向けに微調整(SFT: Supervised Fine-Tuning)を施した'daichira/llm-jp-3-13b-finetune2'から、さらに後述のコードによりSFTを施したモデル`llm-jp-3-13b-itnew9`を公開するものです。このREADMEは、モデルのセットアップ、トレーニング、推論の再現性を確保するための手順を示します。
---
## 前提条件
このプロジェクトを実行するには、以下の環境とツールが必要です:
- Python 3.8以上
- Google Colabまたはローカル環境 (GPU推奨)
- Hugging Faceアクセストークン (HF\_TOKEN)
---
## セットアップ手順
### 1. ライブラリのインストール
Google Colabの場合、以下のコマンドを使用して必要なライブラリをインストールします:
```bash
!pip uninstall unsloth -y && pip install --upgrade --no-cache-dir "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
!pip install --upgrade torch
!pip install --upgrade xformers
!pip install ipywidgets --upgrade
```
Flash Attention 2をサポートするために、以下をインストールします:
```python
import torch
if torch.cuda.get_device_capability()[0] >= 8:
!pip install --no-deps packaging ninja einops "flash-attn>=2.6.3"
```
### 2. モデルとトークナイザーのロード
以下のコードを使用して、Hugging Faceからベースモデルをロードし、LoRAの設定を適用します:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
from unsloth import FastLanguageModel
max_seq_length = 1024
dtype = None
load_in_4bit = True
model_id = "daichira/llm-jp-3-13b-finetune2"
new_model_id = "llm-jp-3-13b-itnew9"
model, tokenizer = FastLanguageModel.from_pretrained(
model_name=model_id,
dtype=dtype,
load_in_4bit=load_in_4bit,
trust_remote_code=True,
)
model = FastLanguageModel.get_peft_model(
model,
r=32,
target_modules=["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"],
lora_alpha=32,
lora_dropout=0.05,
bias="none",
use_gradient_checkpointing="unsloth",
random_state=3407,
use_rslora=False,
loftq_config=None,
max_seq_length=max_seq_length,
)
```
---
## データセットの準備
### データの分割と保存
以下のコードでデータセットをHugging Faceからロードし、分割して保存します:
```python
HF_TOKEN = "Your_token" # Write権限
!pip install datasets
import os
from datasets import load_dataset
dataset = load_dataset("DeL-TaiseiOzaki/Tengentoppa-sft-v1.0", split="train")
chunk_size = 30000
output_dir = "/content/tengentoppa_chunks"
os.makedirs(output_dir, exist_ok=True)
total_rows = len(dataset)
num_chunks = (total_rows + chunk_size - 1) // chunk_size
for i in range(num_chunks):
start_idx = i * chunk_size
end_idx = min(start_idx + chunk_size, total_rows)
chunk = dataset.select(range(start_idx, end_idx))
chunk_file = f"{output_dir}/tengentoppa_chunk_{i+1}.json"
chunk.to_json(chunk_file)
print(f"Saved chunk {i+1}/{num_chunks} to {chunk_file}")
print("All chunks have been saved!")
```
### JSON形式でのデータセット読み込み
以下のコードでJSONデータセットをロードします:
```python
json_path = "/content/tengentoppa_chunks/tengentoppa_chunk_3.json"
dataset = load_dataset("json", data_files=json_path)
print(dataset)
```
---
## トレーニングの設定
以下の手順でトレーニングを設定します:
```python
prompt = """### 指示
{}
### 回答
{}"""
EOS_TOKEN = tokenizer.eos_token
def formatting_prompts_func(examples):
input_text = examples["instruction"]
output_text = examples["output"]
return {"formatted_text": prompt.format(input_text, output_text) + EOS_TOKEN}
dataset = dataset.map(formatting_prompts_func, num_proc=4)
from trl import SFTTrainer
from transformers import TrainingArguments
from unsloth import is_bfloat16_supported
trainer = SFTTrainer(
model=model,
tokenizer=tokenizer,
train_dataset=dataset["train"],
max_seq_length=max_seq_length,
dataset_text_field="formatted_text",
args=TrainingArguments(
per_device_train_batch_size=6,
gradient_accumulation_steps=4,
num_train_epochs=1,
logging_steps=50,
warmup_steps=500,
save_steps=500,
save_total_limit=2,
learning_rate=3e-4,
fp16=not is_bfloat16_supported(),
bf16=is_bfloat16_supported(),
group_by_length=True,
seed=3407,
output_dir="outputs",
),
)
# 学習実行
torch.cuda.empty_cache()
trainer.train()
```
---
## 推論
以下のコードでトレーニング済みモデルを使用して推論を行います:
```python
import json
from tqdm import tqdm
with open("/content/elyza-tasks-100-TV_0.jsonl", "r") as f:
datasets = [json.loads(line) for line in f if line.strip().endswith("}")]
FastLanguageModel.for_inference(model)
results = []
for dt in tqdm(datasets):
input_text = dt["input"]
prompt = f"### 指示\n{input_text}\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_text, "output": prediction})
with open(f"{new_model_id}_output.jsonl", 'w', encoding='utf-8') as f:
for result in results:
json.dump(result, f, ensure_ascii=False)
f.write('\n')
```
---
## 注意事項
- 本モデルは日本語専用で設計されています。
- 再現性を確保するため、ランダムシードを固定しています (`seed=3407`)。
- モデルのパラメータ量が大きいため、十分なGPUメモリを確保してください (推奨: 16GB以上)。
---
## 実行コード全体
```python
# 必要なライブラリのインストール
!pip uninstall unsloth -y && pip install --upgrade --no-cache-dir "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
!pip install --upgrade torch
!pip install --upgrade xformers
!pip install ipywidgets --upgrade
# Flash Attention 2のインストール
import torch
if torch.cuda.get_device_capability()[0] >= 8:
!pip install --no-deps packaging ninja einops "flash-attn>=2.6.3"
# モデルとトークナイザーのロード
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
from unsloth import FastLanguageModel
# モデル設定
max_seq_length = 1024
dtype = None
load_in_4bit = True
model_id = "daichira/llm-jp-3-13b-finetune2"
new_model_id = "llm-jp-3-13b-itnew9"
model, tokenizer = FastLanguageModel.from_pretrained(
model_name=model_id,
dtype=dtype,
load_in_4bit=load_in_4bit,
trust_remote_code=True,
)
# SFT用のモデル設定
model = FastLanguageModel.get_peft_model(
model,
r=32,
target_modules=["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"],
lora_alpha=32,
lora_dropout=0.05,
bias="none",
use_gradient_checkpointing="unsloth",
random_state=3407,
use_rslora=False,
loftq_config=None,
max_seq_length=max_seq_length,
)
# Hugging Faceのトークン設定
HF_TOKEN = "your_token"
# データセットの準備
!pip install datasets
import os
from datasets import load_dataset
dataset = load_dataset("DeL-TaiseiOzaki/Tengentoppa-sft-v1.0", split="train")
chunk_size = 30000
output_dir = "/content/tengentoppa_chunks"
os.makedirs(output_dir, exist_ok=True)
total_rows = len(dataset)
num_chunks = (total_rows + chunk_size - 1) // chunk_size
for i in range(num_chunks):
start_idx = i * chunk_size
end_idx = min(start_idx + chunk_size, total_rows)
chunk = dataset.select(range(start_idx, end_idx))
chunk_file = f"{output_dir}/tengentoppa_chunk_{i+1}.json"
chunk.to_json(chunk_file)
print(f"Saved chunk {i+1}/{num_chunks} to {chunk_file}")
print("All chunks have been saved!")
# JSON形式のデータセットをロード
json_path = "/content/tengentoppa_chunks/tengentoppa_chunk_3.json"
dataset = load_dataset("json", data_files=json_path)
print(dataset)
# プロンプトフォーマットの適用
prompt = """### 指示
{}
### 回答
{}"""
EOS_TOKEN = tokenizer.eos_token
def formatting_prompts_func(examples):
input_text = examples["instruction"]
output_text = examples["output"]
return {"formatted_text": prompt.format(input_text, output_text) + EOS_TOKEN}
dataset = dataset.map(formatting_prompts_func, num_proc=4)
# トレーニングの設定
from trl import SFTTrainer
from transformers import TrainingArguments
from unsloth import is_bfloat16_supported
trainer = SFTTrainer(
model=model,
tokenizer=tokenizer,
train_dataset=dataset["train"],
max_seq_length=max_seq_length,
dataset_text_field="formatted_text",
args=TrainingArguments(
per_device_train_batch_size=6,
gradient_accumulation_steps=4,
num_train_epochs=1,
logging_steps=50,
warmup_steps=500,
save_steps=500,
save_total_limit=2,
learning_rate=3e-4,
fp16=not is_bfloat16_supported(),
bf16=is_bfloat16_supported(),
group_by_length=True,
seed=3407,
output_dir="outputs",
),
)
# 学習実行
torch.cuda.empty_cache()
trainer.train()
# 推論の準備
import json
from tqdm import tqdm
with open("/content/elyza-tasks-100-TV_0.jsonl", "r") as f:
datasets = [json.loads(line) for line in f if line.strip().endswith("}")]
FastLanguageModel.for_inference(model)
results = []
for dt in tqdm(datasets):
input_text = dt["input"]
prompt = f"""### 指示\n{input_text}\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_text, "output": prediction})
# 推論結果の保存
with open(f"{new_model_id}_output.jsonl", 'w', encoding='utf-8') as f:
for result in results:
json.dump(result, f, ensure_ascii=False)
f.write('\n')
```
``` |