Update README.md
Browse files
README.md
CHANGED
@@ -20,3 +20,217 @@ language:
|
|
20 |
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
21 |
|
22 |
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
21 |
|
22 |
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
23 |
+
|
24 |
+
# Instruction Tuning
|
25 |
+
|
26 |
+
The models have been fine-tuned on the following datasets.
|
27 |
+
|
28 |
+
| Language | Dataset | description |
|
29 |
+
|:---|:---|:---|
|
30 |
+
|Japanese|[ichikara-instruction-003-001-1.json](https://liat-aip.sakura.ne.jp/wp/llm%E3%81%AE%E3%81%9F%E3%82%81%E3%81%AE%E6%97%A5%E6%9C%AC%E8%AA%9E%E3%82%A4%E3%83%B3%E3%82%B9%E3%83%88%E3%83%A9%E3%82%AF%E3%82%B7%E3%83%A7%E3%83%B3%E3%83%87%E3%83%BC%E3%82%BF%E4%BD%9C%E6%88%90/llm%E3%81%AE%E3%81%9F%E3%82%81%E3%81%AE%E6%97%A5%E6%9C%AC%E8%AA%9E%E3%82%A4%E3%83%B3%E3%82%B9%E3%83%88%E3%83%A9%E3%82%AF%E3%82%B7%E3%83%A7%E3%83%B3%E3%83%87%E3%83%BC%E3%82%BF-%E5%85%AC%E9%96%8B/)| A manually constructed instruction dataset |
|
31 |
+
|
32 |
+
データセット作成チーム:
|
33 |
+
関根聡, 安藤まや, 後藤美知子, 鈴木久美, 河原大輔, 井之上直也, 乾健太郎. ichikara-instruction: LLMのための日本語インストラクションデータの構築. 言語処理学会第30回年次大会(2024)
|
34 |
+
|
35 |
+
|
36 |
+
# Usage
|
37 |
+
|
38 |
+
以下はElyza-tasks-100-TV_0.jsonlの回答のためのコードです。
|
39 |
+
|
40 |
+
```python
|
41 |
+
from transformers import (
|
42 |
+
AutoModelForCausalLM,
|
43 |
+
AutoTokenizer,
|
44 |
+
BitsAndBytesConfig,
|
45 |
+
TrainingArguments,
|
46 |
+
logging,
|
47 |
+
)
|
48 |
+
from peft import (
|
49 |
+
LoraConfig,
|
50 |
+
PeftModel,
|
51 |
+
get_peft_model,
|
52 |
+
)
|
53 |
+
import os, torch, gc
|
54 |
+
from datasets import load_dataset
|
55 |
+
import bitsandbytes as bnb
|
56 |
+
from trl import SFTTrainer
|
57 |
+
```
|
58 |
+
|
59 |
+
```python
|
60 |
+
# Hugging Face Token
|
61 |
+
HF_TOKEN = "your_token"
|
62 |
+
```
|
63 |
+
|
64 |
+
```python
|
65 |
+
base_model_id = "llm-jp/llm-jp-3-13b"
|
66 |
+
new_model_id = "llm-jp-3-13b-it_lora"
|
67 |
+
```
|
68 |
+
|
69 |
+
```python
|
70 |
+
bnb_config = BitsAndBytesConfig(
|
71 |
+
load_in_4bit=True,
|
72 |
+
bnb_4bit_quant_type="nf4",
|
73 |
+
bnb_4bit_compute_dtype=torch.bfloat16,
|
74 |
+
)
|
75 |
+
|
76 |
+
model = AutoModelForCausalLM.from_pretrained(
|
77 |
+
base_model_id,
|
78 |
+
quantization_config=bnb_config,
|
79 |
+
device_map="auto"
|
80 |
+
)
|
81 |
+
|
82 |
+
tokenizer = AutoTokenizer.from_pretrained(base_model_id, trust_remote_code=True)
|
83 |
+
```
|
84 |
+
|
85 |
+
```python
|
86 |
+
def find_all_linear_names(model):
|
87 |
+
cls = bnb.nn.Linear4bit # 4bit量子化線形層クラスを指定
|
88 |
+
lora_module_names = set() # ここに取得した線形層を保持します。
|
89 |
+
|
90 |
+
# モデル内の全てのモジュールを探索します
|
91 |
+
for name, module in model.named_modules():
|
92 |
+
if isinstance(module, cls): # モジュールが4bit量子化線形層の場合
|
93 |
+
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)
|
94 |
+
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
|
95 |
+
|
96 |
+
# '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
|
97 |
+
if 'lm_head' in lora_module_names:
|
98 |
+
lora_module_names.remove('lm_head')
|
99 |
+
|
100 |
+
return list(lora_module_names) # lora_module_namesをリストに変換して返します。
|
101 |
+
|
102 |
+
modules = find_all_linear_names(model)
|
103 |
+
```
|
104 |
+
|
105 |
+
```python
|
106 |
+
peft_config = LoraConfig(
|
107 |
+
r=16,
|
108 |
+
lora_alpha=32,
|
109 |
+
lora_dropout=0.05,
|
110 |
+
bias="none",
|
111 |
+
task_type="CAUSAL_LM",
|
112 |
+
target_modules=modules,
|
113 |
+
)
|
114 |
+
|
115 |
+
model = get_peft_model(model, peft_config)
|
116 |
+
```
|
117 |
+
|
118 |
+
```python
|
119 |
+
dataset = load_dataset("json", data_files="./ichikara-instruction-003-001-1.json")
|
120 |
+
```
|
121 |
+
|
122 |
+
```python
|
123 |
+
# 学習時のプロンプトフォーマットの定義
|
124 |
+
prompt = """### 指示
|
125 |
+
{}
|
126 |
+
### 回答
|
127 |
+
{}"""
|
128 |
+
|
129 |
+
|
130 |
+
"""
|
131 |
+
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
|
132 |
+
"""
|
133 |
+
EOS_TOKEN = tokenizer.eos_token # トークナイザーのEOSトークン(文末トークン)
|
134 |
+
def formatting_prompts_func(examples):
|
135 |
+
input = examples["text"] # 入力データ
|
136 |
+
output = examples["output"] # 出力データ
|
137 |
+
text = prompt.format(input, output) + EOS_TOKEN # プロンプトの作成
|
138 |
+
return { "formatted_text" : text, } # 新しいフィールド "formatted_text" を返す
|
139 |
+
pass
|
140 |
+
|
141 |
+
# # 各データにフォーマットを適用
|
142 |
+
dataset = dataset.map(
|
143 |
+
formatting_prompts_func,
|
144 |
+
num_proc= 4, # 並列処理数を指定
|
145 |
+
)
|
146 |
+
```
|
147 |
+
|
148 |
+
```python
|
149 |
+
training_arguments = TrainingArguments(
|
150 |
+
output_dir=new_model_id,
|
151 |
+
per_device_train_batch_size=1,
|
152 |
+
gradient_accumulation_steps=2,
|
153 |
+
optim="paged_adamw_32bit",
|
154 |
+
num_train_epochs=1,
|
155 |
+
logging_strategy="steps",
|
156 |
+
logging_steps=10,
|
157 |
+
warmup_steps=10,
|
158 |
+
save_steps=100,
|
159 |
+
save_total_limit = 2,
|
160 |
+
max_steps = -1,
|
161 |
+
learning_rate=5e-5,
|
162 |
+
fp16=False,
|
163 |
+
bf16=False,
|
164 |
+
seed = 3407,
|
165 |
+
group_by_length=True,
|
166 |
+
report_to="none"
|
167 |
+
)
|
168 |
+
```
|
169 |
+
|
170 |
+
```python
|
171 |
+
trainer = SFTTrainer(
|
172 |
+
model=model,
|
173 |
+
train_dataset=dataset["train"],
|
174 |
+
peft_config=peft_config,
|
175 |
+
max_seq_length= 512,
|
176 |
+
dataset_text_field="formatted_text",
|
177 |
+
tokenizer=tokenizer,
|
178 |
+
args=training_arguments,
|
179 |
+
packing= False,
|
180 |
+
)
|
181 |
+
|
182 |
+
model.config.use_cache = False # キャッシュ機能を無効化
|
183 |
+
trainer.train() # トレーニングを実行
|
184 |
+
```
|
185 |
+
|
186 |
+
```python
|
187 |
+
import json
|
188 |
+
datasets = []
|
189 |
+
with open("./elyza-tasks-100-TV_0.jsonl", "r") as f:
|
190 |
+
item = ""
|
191 |
+
for line in f:
|
192 |
+
line = line.strip()
|
193 |
+
item += line
|
194 |
+
if item.endswith("}"):
|
195 |
+
datasets.append(json.loads(item))
|
196 |
+
item = ""
|
197 |
+
```
|
198 |
+
|
199 |
+
```python
|
200 |
+
from tqdm import tqdm
|
201 |
+
|
202 |
+
results = []
|
203 |
+
for data in tqdm(datasets):
|
204 |
+
|
205 |
+
input = data["input"]
|
206 |
+
|
207 |
+
prompt = f"""### 指示
|
208 |
+
{input}
|
209 |
+
### 回答
|
210 |
+
"""
|
211 |
+
|
212 |
+
tokenized_input = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt").to(model.device)
|
213 |
+
attention_mask = torch.ones_like(tokenized_input)
|
214 |
+
|
215 |
+
with torch.no_grad():
|
216 |
+
outputs = model.generate(
|
217 |
+
tokenized_input,
|
218 |
+
attention_mask=attention_mask,
|
219 |
+
max_new_tokens=100,
|
220 |
+
do_sample=False,
|
221 |
+
repetition_penalty=1.2,
|
222 |
+
pad_token_id=tokenizer.eos_token_id
|
223 |
+
)[0]
|
224 |
+
output = tokenizer.decode(outputs[tokenized_input.size(1):], skip_special_tokens=True)
|
225 |
+
|
226 |
+
results.append({"task_id": data["task_id"], "input": input, "output": output})
|
227 |
+
```
|
228 |
+
|
229 |
+
```python
|
230 |
+
import re
|
231 |
+
jsonl_id = re.sub(".*/", "", new_model_id)
|
232 |
+
with open(f"./{jsonl_id}-outputs.jsonl", 'w', encoding='utf-8') as f:
|
233 |
+
for result in results:
|
234 |
+
json.dump(result, f, ensure_ascii=False) # ensure_ascii=False for handling non-ASCII characters
|
235 |
+
f.write('\n')
|
236 |
+
```
|