Commit
•
9e7e902
1
Parent(s):
f509c4b
Update tokenizer_config.json
Browse files- tokenizer_config.json +113 -6
tokenizer_config.json
CHANGED
|
@@ -1,4 +1,10 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"151329": {
|
| 4 |
"content": "<|endoftext|>",
|
|
@@ -7,14 +13,115 @@
|
|
| 7 |
"rstrip": false,
|
| 8 |
"single_word": false,
|
| 9 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
}
|
| 11 |
},
|
| 12 |
-
"
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
null
|
| 16 |
-
]
|
| 17 |
-
},
|
| 18 |
"chat_template": "{% for message in messages %}{% if loop.first %}[gMASK]<sop><|{{ message['role'] }}|>\n {{ message['content'] }}{% else %}<|{{ message['role'] }}|>\n {{ message['content'] }}{% endif %}{% endfor %}{% if add_generation_prompt %}<|assistant|>{% endif %}",
|
| 19 |
"clean_up_tokenization_spaces": false,
|
| 20 |
"do_lower_case": false,
|
|
|
|
| 1 |
{
|
| 2 |
+
"auto_map": {
|
| 3 |
+
"AutoTokenizer": [
|
| 4 |
+
"tokenization_chatglm.ChatGLM4Tokenizer",
|
| 5 |
+
null
|
| 6 |
+
]
|
| 7 |
+
},
|
| 8 |
"added_tokens_decoder": {
|
| 9 |
"151329": {
|
| 10 |
"content": "<|endoftext|>",
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false,
|
| 15 |
"special": true
|
| 16 |
+
},
|
| 17 |
+
"151330": {
|
| 18 |
+
"content": "[MASK]",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false,
|
| 23 |
+
"special": true
|
| 24 |
+
},
|
| 25 |
+
"151331": {
|
| 26 |
+
"content": "[gMASK]",
|
| 27 |
+
"lstrip": false,
|
| 28 |
+
"normalized": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"single_word": false,
|
| 31 |
+
"special": true
|
| 32 |
+
},
|
| 33 |
+
"151332": {
|
| 34 |
+
"content": "[sMASK]",
|
| 35 |
+
"lstrip": false,
|
| 36 |
+
"normalized": false,
|
| 37 |
+
"rstrip": false,
|
| 38 |
+
"single_word": false,
|
| 39 |
+
"special": true
|
| 40 |
+
},
|
| 41 |
+
"151333": {
|
| 42 |
+
"content": "<sop>",
|
| 43 |
+
"lstrip": false,
|
| 44 |
+
"normalized": false,
|
| 45 |
+
"rstrip": false,
|
| 46 |
+
"single_word": false,
|
| 47 |
+
"special": true
|
| 48 |
+
},
|
| 49 |
+
"151334": {
|
| 50 |
+
"content": "<eop>",
|
| 51 |
+
"lstrip": false,
|
| 52 |
+
"normalized": false,
|
| 53 |
+
"rstrip": false,
|
| 54 |
+
"single_word": false,
|
| 55 |
+
"special": true
|
| 56 |
+
},
|
| 57 |
+
"151335": {
|
| 58 |
+
"content": "<|system|>",
|
| 59 |
+
"lstrip": false,
|
| 60 |
+
"normalized": false,
|
| 61 |
+
"rstrip": false,
|
| 62 |
+
"single_word": false,
|
| 63 |
+
"special": true
|
| 64 |
+
},
|
| 65 |
+
"151336": {
|
| 66 |
+
"content": "<|user|>",
|
| 67 |
+
"lstrip": false,
|
| 68 |
+
"normalized": false,
|
| 69 |
+
"rstrip": false,
|
| 70 |
+
"single_word": false,
|
| 71 |
+
"special": true
|
| 72 |
+
},
|
| 73 |
+
"151337": {
|
| 74 |
+
"content": "<|assistant|>",
|
| 75 |
+
"lstrip": false,
|
| 76 |
+
"normalized": false,
|
| 77 |
+
"rstrip": false,
|
| 78 |
+
"single_word": false,
|
| 79 |
+
"special": true
|
| 80 |
+
},
|
| 81 |
+
"151338": {
|
| 82 |
+
"content": "<|observation|>",
|
| 83 |
+
"lstrip": false,
|
| 84 |
+
"normalized": false,
|
| 85 |
+
"rstrip": false,
|
| 86 |
+
"single_word": false,
|
| 87 |
+
"special": true
|
| 88 |
+
},
|
| 89 |
+
"151339": {
|
| 90 |
+
"content": "<|begin_of_image|>",
|
| 91 |
+
"lstrip": false,
|
| 92 |
+
"normalized": false,
|
| 93 |
+
"rstrip": false,
|
| 94 |
+
"single_word": false,
|
| 95 |
+
"special": true
|
| 96 |
+
},
|
| 97 |
+
"151340": {
|
| 98 |
+
"content": "<|end_of_image|>",
|
| 99 |
+
"lstrip": false,
|
| 100 |
+
"normalized": false,
|
| 101 |
+
"rstrip": false,
|
| 102 |
+
"single_word": false,
|
| 103 |
+
"special": true
|
| 104 |
+
},
|
| 105 |
+
"151341": {
|
| 106 |
+
"content": "<|begin_of_video|>",
|
| 107 |
+
"lstrip": false,
|
| 108 |
+
"normalized": false,
|
| 109 |
+
"rstrip": false,
|
| 110 |
+
"single_word": false,
|
| 111 |
+
"special": true
|
| 112 |
+
},
|
| 113 |
+
"151342": {
|
| 114 |
+
"content": "<|end_of_video|>",
|
| 115 |
+
"lstrip": false,
|
| 116 |
+
"normalized": false,
|
| 117 |
+
"rstrip": false,
|
| 118 |
+
"single_word": false,
|
| 119 |
+
"special": true
|
| 120 |
}
|
| 121 |
},
|
| 122 |
+
"additional_special_tokens": ["<|endoftext|>", "[MASK]", "[gMASK]", "[sMASK]", "<sop>", "<eop>", "<|system|>",
|
| 123 |
+
"<|user|>", "<|assistant|>", "<|observation|>", "<|begin_of_image|>", "<|end_of_image|>",
|
| 124 |
+
"<|begin_of_video|>", "<|end_of_video|>"],
|
|
|
|
|
|
|
|
|
|
| 125 |
"chat_template": "{% for message in messages %}{% if loop.first %}[gMASK]<sop><|{{ message['role'] }}|>\n {{ message['content'] }}{% else %}<|{{ message['role'] }}|>\n {{ message['content'] }}{% endif %}{% endfor %}{% if add_generation_prompt %}<|assistant|>{% endif %}",
|
| 126 |
"clean_up_tokenization_spaces": false,
|
| 127 |
"do_lower_case": false,
|