File size: 12,220 Bytes
7934b29 |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"id": "8046e96a",
"metadata": {},
"outputs": [],
"source": [
"BRANCH='r1.17.0'"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "38bfe8ea",
"metadata": {},
"outputs": [],
"source": [
"\"\"\"\n",
"You can run either this notebook locally (if you have all the dependencies and a GPU) or on Google Colab.\n",
"\n",
"Instructions for setting up Colab are as follows:\n",
"1. Open a new Python 3 notebook.\n",
"2. Import this notebook from GitHub (File -> Upload Notebook -> \"GITHUB\" tab -> copy/paste GitHub URL)\n",
"3. Connect to an instance with a GPU (Runtime -> Change runtime type -> select \"GPU\" for hardware accelerator)\n",
"4. Run this cell to set up dependencies.\n",
"\"\"\"\n",
"# If you're using Google Colab and not running locally, run this cell\n",
"\n",
"# install NeMo\n",
"!python -m pip install git+https://github.com/NVIDIA/NeMo.git@$BRANCH#egg=nemo_toolkit[nlp]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "98c00a93",
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"import wget \n",
"import torch\n",
"import pytorch_lightning as pl\n",
"from omegaconf import OmegaConf"
]
},
{
"cell_type": "markdown",
"id": "e9fb1a66",
"metadata": {},
"source": [
"# Task Description\n",
"In this tutorial, we are going to describe how to export NeMo NLP models with BERT based models as the pre-trained model."
]
},
{
"cell_type": "markdown",
"id": "dd0fb016",
"metadata": {},
"source": [
"## Convert the Megatron-LM Weights to Nemo file\n",
"\n",
"If you prefer to use the Huggingface BERT models, please skip this section and refer to `Setting up a NeMo Experiment` section to load a model from `nemo_nlp.modules.get_pretrained_lm_models_list()`\n",
"\n",
"NeMo Megatron BERT can [load from a pretrained model](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/main/core/core.html?highlight=nemo%20file#restore) using `.nemo` file. We can convert the Megatron-LM checkpoint to the `.nemo` file. Let's first download the pretrained model weights and vocabulary file."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e451f219",
"metadata": {},
"outputs": [],
"source": [
"from nemo.collections.nlp.modules.common.megatron.megatron_utils import MEGATRON_CONFIG_MAP\n",
"import pathlib\n",
"\n",
"PRETRAINED_BERT_MODEL = \"megatron-bert-345m-uncased\" # specify BERT-like model from MEGATRON_CONFIG_MAP.keys()\n",
"nemo_out_path = \"qa_pretrained.nemo\" # the nemo output file name\n",
"\n",
"checkpoint_url = MEGATRON_CONFIG_MAP[PRETRAINED_BERT_MODEL]['checkpoint']\n",
"vocab_url = MEGATRON_CONFIG_MAP[PRETRAINED_BERT_MODEL]['vocab']\n",
"checkpoint_filename = pathlib.Path(checkpoint_url).name\n",
"vocab_filename = pathlib.Path(vocab_url).name\n",
"if not pathlib.Path(checkpoint_filename).exists():\n",
" print('downloading from checkpoint url', checkpoint_url)\n",
" !wget $checkpoint_url\n",
"if not pathlib.Path(vocab_filename).exists():\n",
" print('downloading from vocab url', vocab_url)\n",
" !wget $vocab_url"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7586b5c0",
"metadata": {},
"outputs": [],
"source": [
"WORK_DIR = \"WORK_DIR\"\n",
"os.makedirs(WORK_DIR, exist_ok=True)\n",
"\n",
"# Prepare the model parameters \n",
"# download the model's configuration file \n",
"config_dir = WORK_DIR + '/configs/'\n",
"MODEL_CONFIG = \"megatron_bert_config.yaml\"\n",
"os.makedirs(config_dir, exist_ok=True)\n",
"if not os.path.exists(config_dir + MODEL_CONFIG):\n",
" print('Downloading config file...')\n",
" wget.download(f'https://raw.githubusercontent.com/NVIDIA/NeMo/{BRANCH}/examples/nlp/language_modeling/conf/' + MODEL_CONFIG, config_dir)\n",
"else:\n",
" print ('config file is already exists')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e0dd3124",
"metadata": {},
"outputs": [],
"source": [
"# this line will print the entire config of the model\n",
"config_path = f'{WORK_DIR}/configs/{MODEL_CONFIG}'\n",
"print(config_path)\n",
"config = OmegaConf.load(config_path)\n",
"\n",
"config.model.megatron_legacy = True # set to true if you trained the NLP model on NeMo < 1.5.0\n",
"config.model.bias_gelu_fusion = False # set to true if you want the MegatronLM to NeMo conversion for training; and set to false to use the converted model at time of export \n",
"config.model.masked_softmax_fusion = False # set to true if you want the MegatronLM to NeMo conversion for training; and set to false to use the converted model at time of export\n",
"\n",
"config.model.num_layers = 24\n",
"config.model.hidden_size = 1024\n",
"config.model.ffn_hidden_size = 4096\n",
"config.model.num_attention_heads = 16\n",
"config.model.tokenizer.vocab_file = vocab_filename\n",
"config.model.tokenizer.type = 'BertWordPieceLowerCase' # change this to BertWordPieceCase if you are using a cased pretrained model\n",
"config.model.tensor_model_parallel_size = 1\n",
"config.model.data.data_prefix = ''\n",
"config.model.max_position_embeddings = 512\n",
"config.model.data.seq_length = 512\n",
"config.cfg = {}\n",
"config.cfg.cfg = config.model\n",
"with open('hparams.yaml', 'w') as f:\n",
" f.write(OmegaConf.to_yaml(config.cfg))\n",
"if(config.model.megatron_legacy):\n",
" checkpoint_filename = \"model_optim_rng_ca.pt\" #provide path to the pretrained pt file you used during training on NeMo < 1.5.0, for NeMo >= 1.5.0\n",
"print(checkpoint_filename)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "47dca6de",
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"PWD = os.getcwd()\n",
"wget.download(f'https://raw.githubusercontent.com/NVIDIA/NeMo/{BRANCH}/examples/nlp/language_modeling/megatron_lm_ckpt_to_nemo.py')\n",
"!python -m torch.distributed.run --nproc_per_node=1 megatron_lm_ckpt_to_nemo.py --checkpoint_folder=$PWD --checkpoint_name=$checkpoint_filename --hparams_file=$PWD/hparams.yaml --nemo_file_path=$PWD/$nemo_out_path --model_type=bert --tensor_model_parallel_size=1"
]
},
{
"cell_type": "markdown",
"id": "1ae8d31b",
"metadata": {},
"source": [
"# Legacy NLP Bert based model conversion\n",
"\n",
"Step 1: Convert legacy nemo checkpoint to a checkpoint which is currently supported by nemo\n",
"\n",
"Step 2: Use the converted model from step 1 to export the nemo file to the required format"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "86639a3d",
"metadata": {},
"outputs": [],
"source": [
"wget.download(f'https://raw.githubusercontent.com/NVIDIA/NeMo/{BRANCH}/scripts/nemo_legacy_import/nlp_checkpoint_port.py')\n",
"wget.download(f'https://raw.githubusercontent.com/NVIDIA/NeMo/{BRANCH}/scripts/export.py')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "48820d57",
"metadata": {},
"outputs": [],
"source": [
"legacy_nemo_file_path = \"/NeMo/megatron_multiqa.nemo\" #path to you model trained on NeMo < 1.5\n",
"nemo_converted_out_path = \"converted_megatron_multiqa.nemo\"\n",
"megatron_absolute_language_model_path = \"/NeMo/tutorials/nlp/qa_pretrained.nemo\" # Give the absolute path of the model you obtained using megatron_lm_ckpt_to_nemo\n",
"onnx_export_out_path = \"onnx_megatron_multiqa.onnx\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7191e0cb",
"metadata": {},
"outputs": [],
"source": [
"os.system(f\"python nlp_checkpoint_port.py {legacy_nemo_file_path} {nemo_converted_out_path} --megatron-legacy=True --megatron-checkpoint {megatron_absolute_language_model_path}\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ccc720ef",
"metadata": {},
"outputs": [],
"source": [
"os.system(f\"python export.py {nemo_converted_out_path} {onnx_export_out_path} --autocast --runtime-check\")"
]
},
{
"cell_type": "markdown",
"id": "f10461f2",
"metadata": {},
"source": [
"# Convert a NLP model with BERT based pre-trained model trained on NeMo >= 1.5.0\n",
"\n",
"For models trained on NeMo >= 1.5.0, you just run the export script and skip the legacy conversion part"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0514ab37",
"metadata": {},
"outputs": [],
"source": [
"nemo_file_path = \"\"\n",
"onnx_export_out_path = "
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1d6b5db4",
"metadata": {},
"outputs": [],
"source": [
"python export.py $nemo_converted_out_path $onnx_export_out_path --autocast --runtime-check"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.8.12"
}
},
"nbformat": 4,
"nbformat_minor": 5
} |