File size: 7,902 Bytes
17e379b 16226a3 17e379b |
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 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Setup & Installation"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Writing requirements.txt\n"
]
}
],
"source": [
"%%writefile requirements.txt\n",
"bitsandbytes\n",
"git+https://github.com/huggingface/transformers.git\n",
"accelerate\n",
"sentencepiece"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"!pip install -r requirements.txt"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 3. Create Custom Handler for Inference Endpoints\n"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Overwriting pipeline.py\n"
]
}
],
"source": [
"%%writefile pipeline.py\n",
"from typing import Dict, List, Any\n",
"from transformers import AutoTokenizer, AutoModelForCausalLM\n",
"import torch\n",
"\n",
"class PreTrainedPipeline():\n",
" def __init__(self, path=\"\"):\n",
" # load the optimized model\n",
" self.model = AutoModelForCausalLM.from_pretrained(path, torch_dtype=torch.float16, device_map=\"auto\", load_in_8bit=True)\n",
" self.tokenizer = AutoTokenizer.from_pretrained(path)\n",
"\n",
" def __call__(self, data: Any) -> List[List[Dict[str, float]]]:\n",
" \"\"\"\n",
" Args:\n",
" data (:obj:):\n",
" includes the input data and the parameters for the inference.\n",
" Return:\n",
" A :obj:`list`:. The list contains the embeddings of the inference inputs\n",
" \"\"\"\n",
" inputs = data.get(\"inputs\", data)\n",
" parameters = data.get(\"parameters\", {})\n",
"\n",
" # tokenize the input\n",
" input_ids = self.tokenizer(inputs,return_tensors=\"pt\").input_ids.to(self.model.device)\n",
" # run the model\n",
" logits = self.model.generate(input_ids, **parameters)\n",
" # Perform pooling\n",
" # postprocess the prediction\n",
" return {\"generated_text\": self.tokenizer.decode(logits[0].tolist())}"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"test custom pipeline"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"===================================BUG REPORT===================================\n",
"Welcome to bitsandbytes. For bug reports, please submit your error trace to: https://github.com/TimDettmers/bitsandbytes/issues\n",
"For effortless bug reporting copy-paste your error into this form: https://docs.google.com/forms/d/e/1FAIpQLScPB8emS3Thkp66nvqwmjTEgxp8Y9ufuWTzFyr9kJ5AoI47dQ/viewform?usp=sf_link\n",
"================================================================================\n",
"CUDA SETUP: CUDA runtime path found: /home/ubuntu/miniconda/envs/dev/lib/libcudart.so\n",
"CUDA SETUP: Highest compute capability among GPUs detected: 7.5\n",
"CUDA SETUP: Detected CUDA version 113\n",
"CUDA SETUP: Loading binary /home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages/bitsandbytes/libbitsandbytes_cuda113.so...\n"
]
}
],
"source": [
"from pipeline import PreTrainedPipeline\n",
"\n",
"# init handler\n",
"my_handler = PreTrainedPipeline(path=\".\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.\n",
"Setting `pad_token_id` to `eos_token_id`:2 for open-end generation.\n",
"/home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages/transformers/generation_utils.py:1228: UserWarning: Neither `max_length` nor `max_new_tokens` has been set, `max_length` will default to 20 (`self.config.max_length`). Controlling `max_length` via the config is deprecated and `max_length` will be removed from the config in v5 of Transformers -- we recommend using `max_new_tokens` to control the maximum length of the generation.\n",
" warnings.warn(\n",
"/home/ubuntu/miniconda/envs/dev/lib/python3.9/site-packages/transformers/models/codegen/modeling_codegen.py:167: UserWarning: where received a uint8 condition tensor. This behavior is deprecated and will be removed in a future version of PyTorch. Use a boolean condition instead. (Triggered internally at ../aten/src/ATen/native/TensorCompare.cpp:333.)\n",
" attn_weights = torch.where(causal_mask, attn_weights, mask_value)\n"
]
},
{
"data": {
"text/plain": [
"{'generated_text': 'def hello_world():\\n return \"Hello World\"\\n\\[email protected](\\'/'}"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\n",
"# prepare sample payload\n",
"request = {\"inputs\": \"def hello_world():\"}\n",
"\n",
"# test the handler\n",
"my_handler(request)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.\n",
"Setting `pad_token_id` to `eos_token_id`:50256 for open-end generation.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'generated_text': \"# load distilbert model and initialize text-classification pipeline\\nmodel_id = 'distilbert-base-uncased'\\nmodel_url = 'https://tfhub.dev/tensorflow/small_bert/1'\\n\\nmodel_dir = './distilBERT'\"}\n"
]
}
],
"source": [
"# prepare sample payload\n",
"request = {\n",
" \"inputs\": \"# load distilbert model and initialize text-classification pipeline\\nmodel_id = 'distil\",\n",
" \"parameters\": {\n",
" \"top_k\": 100,\n",
" \"max_length\": 64,\n",
" \"early_stopping\": True,\n",
" \"do_sample\": True,\n",
" \"eos_token_id\": 50256,\n",
" },\n",
"}\n",
"\n",
"# test the handler\n",
"print(my_handler(request))\n"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"50256"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"my_handler.tokenizer.convert_tokens_to_ids(my_handler.tokenizer.eos_token)\n"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3.9.13 ('dev': conda)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.13"
},
"orig_nbformat": 4,
"vscode": {
"interpreter": {
"hash": "f6dd96c16031089903d5a31ec148b80aeb0d39c32affb1a1080393235fbfa2fc"
}
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|