Spaces:
Runtime error
Runtime error
File size: 11,608 Bytes
73baeae |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/opt/conda/lib/python3.9/site-packages/tqdm/auto.py:22: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
" from .autonotebook import tqdm as notebook_tqdm\n"
]
}
],
"source": [
"from transformers import AutoTokenizer\n",
"from transformers.models.bart.modeling_bart import BartForConditionalGeneration"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"tokenizer = AutoTokenizer.from_pretrained(\"facebook/bart-large\")"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"('bart/tokenizer/tokenizer_config.json',\n",
" 'bart/tokenizer/special_tokens_map.json',\n",
" 'bart/tokenizer/vocab.json',\n",
" 'bart/tokenizer/merges.txt',\n",
" 'bart/tokenizer/added_tokens.json',\n",
" 'bart/tokenizer/tokenizer.json')"
]
},
"execution_count": 35,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tokenizer.save_pretrained(\"bart/tokenizer\")"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [],
"source": [
"model = BartForConditionalGeneration.from_pretrained(\"facebook/bart-large\", forced_bos_token_id=0)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Some weights of AudioBartForConditionalGeneration were not initialized from the model checkpoint at bart/model/ and are newly initialized: ['model.encodec_embeddings.3.weight', 'model.encodec_embeddings.4.weight', 'model.encodec_embeddings.1.weight', 'model.encodec_embeddings.0.weight', 'model.encoder.encodec_embeddings.7.weight', 'model.encodec_embeddings.2.weight', 'model.encodec_embeddings.6.weight', 'model.encoder.encodec_embeddings.0.weight', 'model.encodec_embeddings.7.weight', 'model.encoder.encodec_embeddings.4.weight', 'model.encoder.encodec_embeddings.2.weight', 'model.encoder.encodec_embeddings.3.weight', 'model.encodec_embeddings.5.weight', 'model.encoder.encodec_embeddings.5.weight', 'model.encoder.encodec_embeddings.1.weight', 'model.encoder.encodec_embeddings.6.weight']\n",
"You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
]
}
],
"source": [
"from modeling.audiobart import AudioBartForConditionalGeneration\n",
"model = AudioBartForConditionalGeneration.from_pretrained(\"bart/model/\")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'input_ids': tensor([[ 0, 31414, 127, 50264, 32440, 3807, 118, 32440, 3807, 118,\n",
" 25610, 2]]), 'attention_mask': tensor([[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]])}\n"
]
}
],
"source": [
"text = \"Hello my <mask> yeppi yeppi yo\"\n",
"input = tokenizer(text, return_tensors='pt')\n",
"print(input)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"generated_ids = model.generate(input[\"input_ids\"])"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {},
"outputs": [],
"source": [
"ids = output.logits.detach().numpy().argmax(-1)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['Hello my friends, yeppi yeppiiyeppiyeppii ye']"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tokenizer.batch_decode(generated_ids, skip_special_tokens=True)"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {},
"outputs": [],
"source": [
"model.save_pretrained(\"bart/model\")"
]
},
{
"cell_type": "code",
"execution_count": 51,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'input_ids': tensor([[ 0, 7842, 330, 506, 1536, 267, 131, 6634, 36807, 571,\n",
" 20920, 127, 766, 16, 32440, 3807, 118, 32440, 3807, 118,\n",
" 25610, 2]]), 'attention_mask': tensor([[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]])}\n"
]
}
],
"source": [
"text = \"adskfalsj;lsdfg Hello my name is yeppi yeppi yo\"\n",
"input = tokenizer(text, return_tensors='pt')\n",
"print(input)"
]
},
{
"cell_type": "code",
"execution_count": 52,
"metadata": {},
"outputs": [],
"source": [
"output = model.forward(**input)"
]
},
{
"cell_type": "code",
"execution_count": 54,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/opt/conda/lib/python3.9/site-packages/transformers/generation/utils.py:1353: UserWarning: Using `max_length`'s default (20) to control the generation length. This behaviour is deprecated and 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"
]
},
{
"data": {
"text/plain": [
"['</s><s>adskfalsj;lsdfg Hello my name is yeppi ye</s>']"
]
},
"execution_count": 54,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tokenizer.batch_decode(model.generate(input['input_ids']))"
]
},
{
"cell_type": "code",
"execution_count": 39,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['<s>Hello my name is yeppi yeppi yo</s>']"
]
},
"execution_count": 39,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tokenizer.batch_decode(input['input_ids'])"
]
},
{
"cell_type": "code",
"execution_count": 45,
"metadata": {},
"outputs": [],
"source": [
"from transformers.models.bart.modeling_bart import shift_tokens_right"
]
},
{
"cell_type": "code",
"execution_count": 48,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"tensor([[ 0, 0, 31414, 127, 766, 16, 32440, 3807, 118, 32440,\n",
" 3807, 118, 25610]])\n"
]
}
],
"source": [
"print(shift_tokens_right(input['input_ids'], pad_token_id=1, decoder_start_token_id=0))"
]
},
{
"cell_type": "code",
"execution_count": 55,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Downloading (…)lve/main/config.json: 100%|██████████| 1.58k/1.58k [00:00<00:00, 589kB/s]\n",
"Downloading (…)olve/main/vocab.json: 100%|██████████| 899k/899k [00:00<00:00, 1.29MB/s]\n",
"Downloading (…)olve/main/merges.txt: 100%|██████████| 456k/456k [00:00<00:00, 884kB/s]\n",
"Downloading (…)/main/tokenizer.json: 100%|██████████| 1.36M/1.36M [00:00<00:00, 7.43MB/s]\n"
]
}
],
"source": [
"cnn_tokenizer = AutoTokenizer.from_pretrained(\"facebook/bart-large-cnn\")"
]
},
{
"cell_type": "code",
"execution_count": 63,
"metadata": {},
"outputs": [],
"source": [
"original_text = \"ArithmeticErrorThe tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey building, and the tallest structure in Paris. Its base is square, measuring 125 metres (410 ft) on each side. During its construction, the Eiffel Tower surpassed the Washington Monument to become the tallest man-made structure in the world, a title it held for 41 years until the Chrysler Building in New York City was finished in 1930. It was the first structure to reach a height of 300 metres. Due to the addition of a broadcasting aerial at the top of the tower in 1957, it is now taller than the Chrysler Building by 5.2 metres (17 ft). Excluding transmitters, the Eiffel Tower is the second tallest free-standing structure in France after the Millau Viaduct.\""
]
},
{
"cell_type": "code",
"execution_count": 68,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['<s>ArithmeticErrorThe tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey building, and the tallest structure in Paris. Its base is square, measuring 125 metres (410 ft) on each side. During its construction, the Eiffel Tower surpassed the Washington Monument to become the tallest man-made structure in the world, a title it held for 41 years until the Chrysler Building in New York City was finished in 1930. It was the first structure to reach a height of 300 metres. Due to the addition of a broadcasting aerial at the top of the tower in 1957, it is now taller than the Chrysler Building by 5.2 metres (17 ft). Excluding transmitters, the Eiffel Tower is the second tallest free-standing structure in France after the Millau Viaduct.</s>']\n"
]
}
],
"source": [
"input = cnn_tokenizer(text=original_text, return_tensors='pt')\n",
"print(cnn_tokenizer.batch_decode(input['input_ids']))"
]
},
{
"cell_type": "code",
"execution_count": 65,
"metadata": {},
"outputs": [],
"source": [
"cnn_model = BartForConditionalGeneration.from_pretrained(\"facebook/bart-large-cnn\")"
]
},
{
"cell_type": "code",
"execution_count": 66,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/opt/conda/lib/python3.9/site-packages/transformers/generation/utils.py:1353: UserWarning: Using `max_length`'s default (142) to control the generation length. This behaviour is deprecated and 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"
]
},
{
"data": {
"text/plain": [
"['</s><s>The tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey building. During its construction, the Eiffel Tower surpassed the Washington Monument to become the tallest man-made structure in the world. It was the first structure to reach a height of 300 metres.</s>']"
]
},
"execution_count": 66,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cnn_tokenizer.batch_decode(cnn_model.generate(input['input_ids']))"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "base",
"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": "3.9.12"
},
"orig_nbformat": 4
},
"nbformat": 4,
"nbformat_minor": 2
}
|