Update special tokens
Browse filesReplace unused tokens in the chat template with special tokens.
- tokenizer_config.json +76 -2
tokenizer_config.json
CHANGED
|
@@ -11,5 +11,79 @@
|
|
| 11 |
"model_max_length": 1000000000000000019884624838656,
|
| 12 |
"pad_token": "</s>",
|
| 13 |
"tokenizer_class": "InternLMTokenizer",
|
| 14 |
-
"unk_token": "<unk>"
|
| 15 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
"model_max_length": 1000000000000000019884624838656,
|
| 12 |
"pad_token": "</s>",
|
| 13 |
"tokenizer_class": "InternLMTokenizer",
|
| 14 |
+
"unk_token": "<unk>",
|
| 15 |
+
"added_tokens_decoder": {
|
| 16 |
+
"0": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false,
|
| 22 |
+
"special": true
|
| 23 |
+
},
|
| 24 |
+
"1": {
|
| 25 |
+
"content": "<s>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false,
|
| 30 |
+
"special": true
|
| 31 |
+
},
|
| 32 |
+
"2": {
|
| 33 |
+
"content": "</s>",
|
| 34 |
+
"lstrip": false,
|
| 35 |
+
"normalized": false,
|
| 36 |
+
"rstrip": false,
|
| 37 |
+
"single_word": false,
|
| 38 |
+
"special": true
|
| 39 |
+
},
|
| 40 |
+
"92543": {
|
| 41 |
+
"content": "<|im_start|>",
|
| 42 |
+
"lstrip": false,
|
| 43 |
+
"normalized": false,
|
| 44 |
+
"rstrip": false,
|
| 45 |
+
"single_word": false,
|
| 46 |
+
"special": true
|
| 47 |
+
},
|
| 48 |
+
"92542": {
|
| 49 |
+
"content": "<|im_end|>",
|
| 50 |
+
"lstrip": false,
|
| 51 |
+
"normalized": false,
|
| 52 |
+
"rstrip": false,
|
| 53 |
+
"single_word": false,
|
| 54 |
+
"special": true
|
| 55 |
+
},
|
| 56 |
+
"92541": {
|
| 57 |
+
"content": "<|action_start|>",
|
| 58 |
+
"lstrip": false,
|
| 59 |
+
"normalized": false,
|
| 60 |
+
"rstrip": false,
|
| 61 |
+
"single_word": false,
|
| 62 |
+
"special": true
|
| 63 |
+
},
|
| 64 |
+
"92540": {
|
| 65 |
+
"content": "<|action_end|>",
|
| 66 |
+
"lstrip": false,
|
| 67 |
+
"normalized": false,
|
| 68 |
+
"rstrip": false,
|
| 69 |
+
"single_word": false,
|
| 70 |
+
"special": true
|
| 71 |
+
},
|
| 72 |
+
"92539": {
|
| 73 |
+
"content": "<|interpreter|>",
|
| 74 |
+
"lstrip": false,
|
| 75 |
+
"normalized": false,
|
| 76 |
+
"rstrip": false,
|
| 77 |
+
"single_word": false,
|
| 78 |
+
"special": true
|
| 79 |
+
},
|
| 80 |
+
"92538": {
|
| 81 |
+
"content": "<|plugin|>",
|
| 82 |
+
"lstrip": false,
|
| 83 |
+
"normalized": false,
|
| 84 |
+
"rstrip": false,
|
| 85 |
+
"single_word": false,
|
| 86 |
+
"special": true
|
| 87 |
+
}
|
| 88 |
+
}
|
| 89 |
+
}
|