Upload tokenizer
Browse files- added_tokens.json +1 -3
- special_tokens_map.json +2 -2
- tokenizer.json +0 -18
- tokenizer_config.json +2 -18
added_tokens.json
CHANGED
|
@@ -36,7 +36,5 @@
|
|
| 36 |
" ": 50260,
|
| 37 |
" ": 50259,
|
| 38 |
" ": 50258,
|
| 39 |
-
" ": 50257
|
| 40 |
-
"<|im_end|>": 50296,
|
| 41 |
-
"<|im_start|>": 50295
|
| 42 |
}
|
|
|
|
| 36 |
" ": 50260,
|
| 37 |
" ": 50259,
|
| 38 |
" ": 50258,
|
| 39 |
+
" ": 50257
|
|
|
|
|
|
|
| 40 |
}
|
special_tokens_map.json
CHANGED
|
@@ -7,13 +7,13 @@
|
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
-
"content": "<|
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
-
"pad_token": "
|
| 17 |
"unk_token": {
|
| 18 |
"content": "<|endoftext|>",
|
| 19 |
"lstrip": false,
|
|
|
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
"unk_token": {
|
| 18 |
"content": "<|endoftext|>",
|
| 19 |
"lstrip": false,
|
tokenizer.json
CHANGED
|
@@ -353,24 +353,6 @@
|
|
| 353 |
"rstrip": false,
|
| 354 |
"normalized": true,
|
| 355 |
"special": false
|
| 356 |
-
},
|
| 357 |
-
{
|
| 358 |
-
"id": 50295,
|
| 359 |
-
"content": "<|im_start|>",
|
| 360 |
-
"single_word": false,
|
| 361 |
-
"lstrip": false,
|
| 362 |
-
"rstrip": false,
|
| 363 |
-
"normalized": true,
|
| 364 |
-
"special": false
|
| 365 |
-
},
|
| 366 |
-
{
|
| 367 |
-
"id": 50296,
|
| 368 |
-
"content": "<|im_end|>",
|
| 369 |
-
"single_word": false,
|
| 370 |
-
"lstrip": false,
|
| 371 |
-
"rstrip": false,
|
| 372 |
-
"normalized": false,
|
| 373 |
-
"special": true
|
| 374 |
}
|
| 375 |
],
|
| 376 |
"normalizer": null,
|
|
|
|
| 353 |
"rstrip": false,
|
| 354 |
"normalized": true,
|
| 355 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 356 |
}
|
| 357 |
],
|
| 358 |
"normalizer": null,
|
tokenizer_config.json
CHANGED
|
@@ -312,29 +312,13 @@
|
|
| 312 |
"rstrip": false,
|
| 313 |
"single_word": false,
|
| 314 |
"special": false
|
| 315 |
-
},
|
| 316 |
-
"50295": {
|
| 317 |
-
"content": "<|im_start|>",
|
| 318 |
-
"lstrip": false,
|
| 319 |
-
"normalized": true,
|
| 320 |
-
"rstrip": false,
|
| 321 |
-
"single_word": false,
|
| 322 |
-
"special": false
|
| 323 |
-
},
|
| 324 |
-
"50296": {
|
| 325 |
-
"content": "<|im_end|>",
|
| 326 |
-
"lstrip": false,
|
| 327 |
-
"normalized": false,
|
| 328 |
-
"rstrip": false,
|
| 329 |
-
"single_word": false,
|
| 330 |
-
"special": true
|
| 331 |
}
|
| 332 |
},
|
| 333 |
"bos_token": "<|endoftext|>",
|
| 334 |
"clean_up_tokenization_spaces": true,
|
| 335 |
-
"eos_token": "<|
|
| 336 |
"model_max_length": 2048,
|
| 337 |
-
"pad_token": "
|
| 338 |
"tokenizer_class": "CodeGenTokenizer",
|
| 339 |
"unk_token": "<|endoftext|>"
|
| 340 |
}
|
|
|
|
| 312 |
"rstrip": false,
|
| 313 |
"single_word": false,
|
| 314 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 315 |
}
|
| 316 |
},
|
| 317 |
"bos_token": "<|endoftext|>",
|
| 318 |
"clean_up_tokenization_spaces": true,
|
| 319 |
+
"eos_token": "<|endoftext|>",
|
| 320 |
"model_max_length": 2048,
|
| 321 |
+
"pad_token": "<|endoftext|>",
|
| 322 |
"tokenizer_class": "CodeGenTokenizer",
|
| 323 |
"unk_token": "<|endoftext|>"
|
| 324 |
}
|