Delete tokenizer.json
Browse files- tokenizer.json +0 -52
tokenizer.json
DELETED
|
@@ -1,52 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"version": "1.0",
|
| 3 |
-
"truncation": null,
|
| 4 |
-
"padding": null,
|
| 5 |
-
"added_tokens": [
|
| 6 |
-
{
|
| 7 |
-
"id": 0,
|
| 8 |
-
"content": "<|endoftext|>",
|
| 9 |
-
"single_word": false,
|
| 10 |
-
"lstrip": false,
|
| 11 |
-
"rstrip": false,
|
| 12 |
-
"normalized": false,
|
| 13 |
-
"special": true
|
| 14 |
-
},
|
| 15 |
-
{
|
| 16 |
-
"id": 1,
|
| 17 |
-
"content": "<|im_start|>",
|
| 18 |
-
"single_word": false,
|
| 19 |
-
"lstrip": false,
|
| 20 |
-
"rstrip": false,
|
| 21 |
-
"normalized": false,
|
| 22 |
-
"special": true
|
| 23 |
-
},
|
| 24 |
-
{
|
| 25 |
-
"id": 2,
|
| 26 |
-
"content": "<|im_end|>",
|
| 27 |
-
"single_word": false,
|
| 28 |
-
"lstrip": false,
|
| 29 |
-
"rstrip": false,
|
| 30 |
-
"normalized": false,
|
| 31 |
-
"special": true
|
| 32 |
-
}
|
| 33 |
-
],
|
| 34 |
-
"normalizer": null,
|
| 35 |
-
"pre_tokenizer": {
|
| 36 |
-
"type": "Whitespace"
|
| 37 |
-
},
|
| 38 |
-
"post_processor": null,
|
| 39 |
-
"decoder": null,
|
| 40 |
-
"model": {
|
| 41 |
-
"type": "BPE",
|
| 42 |
-
"dropout": null,
|
| 43 |
-
"unk_token": "<|endoftext|>",
|
| 44 |
-
"continuing_subword_prefix": null,
|
| 45 |
-
"end_of_word_suffix": null,
|
| 46 |
-
"fuse_unk": false,
|
| 47 |
-
"byte_fallback": false,
|
| 48 |
-
"ignore_merges": false,
|
| 49 |
-
"vocab": {},
|
| 50 |
-
"merges": []
|
| 51 |
-
}
|
| 52 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|