Commit
•
6b46874
1
Parent(s):
71670d1
Upload tokenizer_config.json with huggingface_hub
Browse files- tokenizer_config.json +67 -0
tokenizer_config.json
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_map": {
|
| 3 |
+
"AutoTokenizer": ["tokenization_baichuan.BaichuanTokenizer", null]
|
| 4 |
+
},
|
| 5 |
+
"add_bos_token": false,
|
| 6 |
+
"add_eos_token": false,
|
| 7 |
+
"use_fast": false,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"__type": "AddedToken",
|
| 11 |
+
"content": "</s>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": true,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": true
|
| 16 |
+
},
|
| 17 |
+
"model_max_length": 4096,
|
| 18 |
+
"sp_model_kwargs": {},
|
| 19 |
+
"tokenizer_class": "BaichuanTokenizer",
|
| 20 |
+
"pad_token": {
|
| 21 |
+
"__type": "AddedToken",
|
| 22 |
+
"content": "<unk>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": true
|
| 27 |
+
},
|
| 28 |
+
"unk_token": {
|
| 29 |
+
"__type": "AddedToken",
|
| 30 |
+
"content": "<unk>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": true,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": true
|
| 35 |
+
},
|
| 36 |
+
"added_tokens_decoder": {
|
| 37 |
+
"125696": {
|
| 38 |
+
"content": "<|EOD|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"125697": {
|
| 46 |
+
"content": "<|MASK|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"125698": {
|
| 54 |
+
"content": "<|PAD|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
}
|
| 61 |
+
},
|
| 62 |
+
"additional_special_tokens": [
|
| 63 |
+
"<|EOD|>",
|
| 64 |
+
"<|MASK|>",
|
| 65 |
+
"<|PAD|>"
|
| 66 |
+
]
|
| 67 |
+
}
|