Update special tokens
#1
by
unsubscribe
- opened
- tokenizer_config.json +62 -13
tokenizer_config.json
CHANGED
|
@@ -1,4 +1,17 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
"content": "<unk>",
|
|
@@ -23,19 +36,55 @@
|
|
| 23 |
"rstrip": false,
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
}
|
| 27 |
},
|
| 28 |
-
"
|
| 29 |
-
"AutoTokenizer": [
|
| 30 |
-
"tokenization_internlm.InternLMTokenizer",
|
| 31 |
-
null
|
| 32 |
-
]
|
| 33 |
-
},
|
| 34 |
-
"bos_token": "<s>",
|
| 35 |
-
"clean_up_tokenization_spaces": false,
|
| 36 |
-
"eos_token": "</s>",
|
| 37 |
-
"model_max_length": 1000000000000000019884624838656,
|
| 38 |
-
"pad_token": "</s>",
|
| 39 |
-
"tokenizer_class": "InternLMTokenizer",
|
| 40 |
-
"unk_token": "<unk>"
|
| 41 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"auto_map": {
|
| 3 |
+
"AutoTokenizer": [
|
| 4 |
+
"tokenization_internlm.InternLMTokenizer",
|
| 5 |
+
null
|
| 6 |
+
]
|
| 7 |
+
},
|
| 8 |
+
"bos_token": "<s>",
|
| 9 |
+
"clean_up_tokenization_spaces": false,
|
| 10 |
+
"eos_token": "</s>",
|
| 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>",
|
|
|
|
| 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 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 90 |
}
|