File size: 11,730 Bytes
ff43179 96786e2 ff43179 fec9aea ff43179 |
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 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Deploy LLaVA on Amazon SageMaker\n",
"\n",
"Amazon SageMaker is a popular platform for running AI models, and models on huggingface deploy [Hugging Face Transformers](https://github.com/huggingface/transformers) using [Amazon SageMaker](https://docs.aws.amazon.com/sagemaker/latest/dg/whatis.html) and the [Amazon SageMaker Python SDK](https://sagemaker.readthedocs.io/en/stable/).\n",
"\n",
"![llava](https://i.imgur.com/YNVG140.png)\n",
"\n",
"Install sagemaker sdk:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"!pip install sagemaker --upgrade\n",
"!pip install -r code/requirements.txt"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Bundle llava model weights and code into a `model.tar.gz`:"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"# Create SageMaker model.tar.gz artifact\n",
"!tar -cf model.tar.gz --use-compress-program=pigz *"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"After we created the `model.tar.gz` archive we can upload it to Amazon S3. We will use the `sagemaker` SDK to upload the model to our sagemaker session bucket.\n",
"\n",
"Initialize sagemaker session first:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import sagemaker\n",
"import boto3\n",
"sess = sagemaker.Session()\n",
"# sagemaker session bucket -> used for uploading data, models and logs\n",
"# sagemaker will automatically create this bucket if it not exists\n",
"sagemaker_session_bucket=None\n",
"if sagemaker_session_bucket is None and sess is not None:\n",
" # set to default bucket if a bucket name is not given\n",
" sagemaker_session_bucket = sess.default_bucket()\n",
"\n",
"try:\n",
" role = sagemaker.get_execution_role()\n",
"except ValueError:\n",
" iam = boto3.client('iam')\n",
" # setup your own rolename in sagemaker\n",
" role = iam.get_role(RoleName='AmazonSageMaker-ExecutionRole-20231008T201275')['Role']['Arn']\n",
"\n",
"sess = sagemaker.Session(default_bucket=sagemaker_session_bucket)\n",
"\n",
"print(f\"sagemaker role arn: {role}\")\n",
"print(f\"sagemaker bucket: {sess.default_bucket()}\")\n",
"print(f\"sagemaker session region: {sess.boto_region_name}\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Upload the `model.tar.gz` to our sagemaker session bucket:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from sagemaker.s3 import S3Uploader\n",
"\n",
"# upload model.tar.gz to s3\n",
"s3_model_uri = S3Uploader.upload(local_path=\"./model.tar.gz\", desired_s3_uri=f\"s3://{sess.default_bucket()}/llava-v1.5-13b\")\n",
"\n",
"print(f\"model uploaded to: {s3_model_uri}\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We will use `HuggingfaceModel` to create our real-time inference endpoint:"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"sagemaker.config INFO - Not applying SDK defaults from location: /Library/Application Support/sagemaker/config.yaml\n",
"sagemaker.config INFO - Not applying SDK defaults from location: /Users/tom/Library/Application Support/sagemaker/config.yaml\n",
"sagemaker.config INFO - Not applying SDK defaults from location: /Library/Application Support/sagemaker/config.yaml\n",
"sagemaker.config INFO - Not applying SDK defaults from location: /Users/tom/Library/Application Support/sagemaker/config.yaml\n",
"---------------!"
]
}
],
"source": [
"\n",
"from sagemaker.huggingface.model import HuggingFaceModel\n",
"\n",
"# create Hugging Face Model Class\n",
"huggingface_model = HuggingFaceModel(\n",
" model_data=s3_model_uri, # path to your model and script\n",
" role=role, # iam role with permissions to create an Endpoint\n",
" transformers_version=\"4.28.1\", # transformers version used\n",
" pytorch_version=\"2.0.0\", # pytorch version used\n",
" py_version='py310', # python version used\n",
" model_server_workers=1\n",
")\n",
"\n",
"# deploy the endpoint endpoint\n",
"predictor = huggingface_model.deploy(\n",
" initial_instance_count=1,\n",
" instance_type=\"ml.g5.xlarge\",\n",
" # container_startup_health_check_timeout=600, # increase timeout for large models\n",
" # model_data_download_timeout=600, # increase timeout for large models\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The `.deploy()` returns an `HuggingFacePredictor` object which can be used to request inference using the `.predict()` method. Our endpoint expects a `json` with at least `image` and `question` key."
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"The image is a black and white photograph of a man standing in front of a building. The man is wearing a suit and tie, and he appears to be looking at the camera. The building in the background is large and has many windows. The overall atmosphere of the image is formal and professional.\n"
]
}
],
"source": [
"data = {\n",
" \"image\" : 'https://raw.githubusercontent.com/haotian-liu/LLaVA/main/images/llava_logo.png', \n",
" \"question\" : \"Describe the image and color details.\",\n",
" # \"max_new_tokens\" : 1024,\n",
" # \"temperature\" : 0.2,\n",
" # \"stop_str\" : \"###\"\n",
"}\n",
"\n",
"# request\n",
"output = predictor.predict(data)\n",
"print(output)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"To run inference with `llava` special token:"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"The image features a red toy animal, possibly a horse or a donkey, with a pair of glasses on its face. The toy is made of plastic and has a fire-like appearance, giving it a unique and eye-catching look. The red color of the toy and the glasses on its face create a striking contrast against the background, making it the main focus of the image.\n"
]
}
],
"source": [
"from llava.conversation import conv_templates, SeparatorStyle\n",
"from llava.constants import (\n",
"DEFAULT_IMAGE_TOKEN,\n",
"DEFAULT_IM_START_TOKEN,\n",
"DEFAULT_IM_END_TOKEN,\n",
")\n",
"def get_prompt(raw_prompt):\n",
" conv_mode = \"llava_v1\"\n",
" conv = conv_templates[conv_mode].copy()\n",
" roles = conv.roles\n",
" inp = f\"{roles[0]}: {raw_prompt}\"\n",
" inp = (\n",
" DEFAULT_IM_START_TOKEN + DEFAULT_IMAGE_TOKEN + DEFAULT_IM_END_TOKEN + \"\\n\" + inp\n",
" )\n",
" conv.append_message(conv.roles[0], inp)\n",
" conv.append_message(conv.roles[1], None)\n",
" prompt = conv.get_prompt()\n",
" stop_str = conv.sep if conv.sep_style != SeparatorStyle.TWO else conv.sep2\n",
" return prompt, stop_str\n",
"\n",
"raw_prompt = \"Describe the image and color details.\"\n",
"prompt, stop_str = get_prompt(raw_prompt)\n",
"image_path = \"https://raw.githubusercontent.com/haotian-liu/LLaVA/main/images/llava_logo.png\"\n",
"data = {\"image\" : image_path, \"question\" : prompt, \"stop_str\" : stop_str}\n",
"output = predictor.predict(data)\n",
"print(output)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The inference ` predictor` can also be initilized like with your deployed `endpoint_name` :"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"sagemaker.config INFO - Not applying SDK defaults from location: /Library/Application Support/sagemaker/config.yaml\n",
"sagemaker.config INFO - Not applying SDK defaults from location: /Users/tom/Library/Application Support/sagemaker/config.yaml\n",
"sagemaker.config INFO - Not applying SDK defaults from location: /Library/Application Support/sagemaker/config.yaml\n",
"sagemaker.config INFO - Not applying SDK defaults from location: /Users/tom/Library/Application Support/sagemaker/config.yaml\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Couldn't call 'get_role' to get Role ARN from role name arn:aws:iam::297308036828:root to get Role path.\n"
]
}
],
"source": [
"import sagemaker\n",
"import boto3\n",
"sess = sagemaker.Session()\n",
"try:\n",
" role = sagemaker.get_execution_role()\n",
"except ValueError:\n",
" iam = boto3.client('iam')\n",
" # setup your own rolename in sagemaker\n",
" role = iam.get_role(RoleName='AmazonSageMaker-ExecutionRole-20231008T201275')['Role']['Arn']\n",
"\n",
"from sagemaker.huggingface.model import HuggingFacePredictor\n",
"# initial the endpoint predictor\n",
"predictor2 = HuggingFacePredictor(\n",
" endpoint_name=\"huggingface-pytorch-inference-2023-10-19-05-57-37-847\",\n",
" sagemaker_session=sess\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"The image features a small toy animal, resembling a horse or a donkey, with a red and orange color scheme. The toy has a pair of glasses on its face, giving it a unique and quirky appearance. The toy is standing on a gray surface, which provides a contrasting background for the vibrant colors of the toy. The combination of red, orange, and gray creates a visually striking scene.\n"
]
}
],
"source": [
"raw_prompt = \"Describe the image and color details.\"\n",
"prompt, stop_str = get_prompt(raw_prompt)\n",
"image_path = \"https://raw.githubusercontent.com/haotian-liu/LLaVA/main/images/llava_logo.png\"\n",
"data = {\"image\" : image_path, \"question\" : prompt, \"stop_str\" : stop_str}\n",
"output = predictor2.predict(data)\n",
"print(output)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"To clean up, we can delete the model and endpoint by `delete_endpoint()`or using sagemaker console:"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
"# delete sagemaker endpoint\n",
"predictor.delete_endpoint()"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "llava",
"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": "3.10.13"
},
"orig_nbformat": 4
},
"nbformat": 4,
"nbformat_minor": 2
}
|