File size: 9,420 Bytes
b3ec055 |
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 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# QA Legal Refugees Project"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Environment\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"! pip install -U \"transformers==4.38.0\" --upgrade\n",
"! pip install git+https://github.com/huggingface/trl\n",
"! pip install peft\n",
"! pip install accelerate\n",
"! pip intall datasets\n",
"! pip install bitsandbytes"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Base Model"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We used Gemma 7b as base model for 3 reason\n",
"- Tokenizer size with multiple [languages](https://www.shelpuk.com/post/llm-practitioner-s-guide-gemma-a-game-changing-multilingual-llm)\n",
"- is SOTA for its size \n",
"- A lot of material available to consult"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Dataset preparation"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We wanted to make a conversation model so we investigated the base model prompt in order to make conversational base on [chatml format](https://github.com/MicrosoftDocs/azure-docs/blob/main/articles/ai-services/openai/includes/chat-markup-language.md#working-with-chat-markup-language-chatml)\n",
"\n",
"we identified the special tokens so the model could understand the different roles in the conversation\n",
"\n",
"Example \n",
"```\n",
"<bos><|im_start|>system\n",
"You are Gemma.<|im_end|>\n",
"<|im_start|>user\n",
"Hello, how are you?<|im_end|>\n",
"<|im_start|>assistant\n",
"I'm doing great. How can I help you today?<|im_end|>\\n<eos>\n",
"```"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"so we used [Phil Schmid's gemma chatml tokenizer](https://huggingface.co/philschmid/gemma-tokenizer-chatml) to adapt our dataset for training"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"## load dataset\n",
"from datasets import load_dataset\n",
"\n",
"dataset = load_dataset(\"somosnlp/instruct-legal-refugiados-es\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# load tokenizer \n",
"tokenizer_id = \"philschmid/gemma-tokenizer-chatml\"\n",
"tokenizer = AutoTokenizer.from_pretrained(tokenizer_id)\n",
"tokenizer.padding_side = 'right' # to prevent warnings"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"## Map functions\n",
"def create_message_column(row):\n",
" messages = []\n",
" user = {\n",
" \"content\": f\"{row['instruction']}/n{row['input']}\",\n",
" \"role\": \"user\"\n",
" }\n",
" messages.append(user)\n",
" assistant = {\n",
" \"content\": f\"{row['output']}\",\n",
" \"role\": \"assistant\"\n",
" }\n",
" messages.append(assistant)\n",
" return {\"messages\": messages}\n",
"\n",
"def format_dataset_chatml(row):\n",
" return {\"text\": tokenizer.apply_chat_template(row[\"messages\"], add_generation_prompt=False, tokenize=False)}"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"## prepare the dataset\n",
"dataset = dataset.map(create_message_column)\n",
"dataset = dataset.map(format_dataset_chatml)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Train Model"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"To finetune Gemma we used PEFT, Lora and SFTTtrainer. The model was trained in a RTX 4090 from Vast.ai founded by the author"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import torch\n",
"from transformers import AutoModelForCausalLM, BitsAndBytesConfig\n",
"\n",
"# cache_dir was set because the rent machine didn't have space in default directory\n",
"# Hugging Face model id\n",
"model_id = \"google/gemma-7b\"\n",
"\n",
"# BitsAndBytesConfig int-4 config\n",
"bnb_config = BitsAndBytesConfig(\n",
" load_in_4bit=True, bnb_4bit_use_double_quant=True, bnb_4bit_quant_type=\"nf4\", bnb_4bit_compute_dtype=torch.bfloat16\n",
")\n",
"\n",
"# Load model and tokenizer\n",
"model = AutoModelForCausalLM.from_pretrained(\n",
" model_id,\n",
" device_map=\"auto\",\n",
" attn_implementation=\"flash_attention_2\",\n",
" torch_dtype=torch.bfloat16,\n",
" quantization_config=bnb_config,\n",
" cache_dir=\"/sys/fs/cgroup/models\"\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from peft import LoraConfig\n",
"\n",
"peft_config = LoraConfig(\n",
" lora_alpha=8,\n",
" lora_dropout=0.05,\n",
" r=6,\n",
" bias=\"none\",\n",
" target_modules=\"all-linear\",\n",
" task_type=\"CAUSAL_LM\"\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from transformers import TrainingArguments\n",
"\n",
"args = TrainingArguments(\n",
" output_dir=\"/sys/fs/cgroup/models/model/location\",\n",
" num_train_epochs=3,\n",
" per_device_train_batch_size=2,\n",
" gradient_accumulation_steps=2,\n",
" gradient_checkpointing=True,\n",
" optim=\"adamw_torch_fused\",\n",
" logging_steps=10,\n",
" save_strategy=\"epoch\",\n",
" bf16=True,\n",
" tf32=True,\n",
" max_grad_norm=0.3, # max gradient norm based on QLoRA paper\n",
" warmup_ratio=0.03, # warmup ratio based on QLoRA paper\n",
" lr_scheduler_type=\"constant\", # use constant learning rate scheduler\n",
" push_to_hub=True,\n",
" hub_private_repo=True,\n",
" hub_model_id=\"model_name\", # push model to hub\n",
" report_to=\"wandb\",\n",
" seed=66,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from trl import SFTTrainer\n",
"\n",
"max_seq_length =1512\n",
"\n",
"trainer = SFTTrainer(\n",
" model=model,\n",
" args=args,\n",
" train_dataset=dataset,\n",
" dataset_text_field=\"text\",\n",
" peft_config=peft_config,\n",
" max_seq_length=max_seq_length,\n",
" tokenizer=tokenizer,\n",
" packing=True,\n",
" dataset_kwargs={\n",
" \"add_special_tokens\": False, # We template with special tokens\n",
" \"append_concat_token\": False, # No need to add additional separator token\n",
" }\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"trainer.train()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"trainer.push_to_hub()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Merge adapter into original model\n",
"When using QLoRA, we only train adapters and not the full model. This means when saving the model during training we only save the adapter weights and not the full model. You can merge the adapter weights into the model weights using the `merge_and_unload` method and then save the model with the `save_pretrained` method."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from peft import PeftModel, PeftConfig\n",
"from transformers import AutoModelForCausalLM\n",
"\n",
"peft_model_id = \"model_name\"\n",
"base_model_id = \"google/gemma-7b-it\"\n",
"config = PeftConfig.from_pretrained(peft_model_id, cache_dir=\"/sys/fs/cgroup/models\")\n",
"model = AutoModelForCausalLM.from_pretrained(base_model_id, cache_dir=\"/sys/fs/cgroup/models\")\n",
"model = PeftModel.from_pretrained(model, peft_model_id ,cache_dir=\"/sys/fs/cgroup/models\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"tokenizer = AutoTokenizer.from_pretrained(peft_model_id, cache_dir=\"/sys/fs/cgroup/models\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"model = model.merge_and_unload()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"model.save_pretrained(\"/sys/fs/cgroup/model/location\", push_to_hub=True, private=True)\n",
"tokenizer.save_pretrained(\"/sys/fs/cgroup/model/location\", push_to_hub=True, private=True)"
]
}
],
"metadata": {
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|