Upload tokenizer
Browse files- special_tokens_map.json +28 -2
- tokenizer.json +27 -0
- tokenizer_config.json +28 -2
special_tokens_map.json
CHANGED
|
@@ -1,7 +1,33 @@
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
-
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
],
|
| 6 |
"bos_token": {
|
| 7 |
"content": "<|bos|>",
|
|
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<|user|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "<|assistant|>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"content": "<|system|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
],
|
| 32 |
"bos_token": {
|
| 33 |
"content": "<|bos|>",
|
tokenizer.json
CHANGED
|
@@ -79,6 +79,33 @@
|
|
| 79 |
"rstrip": false,
|
| 80 |
"normalized": false,
|
| 81 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 82 |
}
|
| 83 |
],
|
| 84 |
"normalizer": {
|
|
|
|
| 79 |
"rstrip": false,
|
| 80 |
"normalized": false,
|
| 81 |
"special": true
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"id": 32005,
|
| 85 |
+
"content": "<|user|>",
|
| 86 |
+
"single_word": false,
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"id": 32006,
|
| 94 |
+
"content": "<|assistant|>",
|
| 95 |
+
"single_word": false,
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"normalized": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"id": 32007,
|
| 103 |
+
"content": "<|system|>",
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"lstrip": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"normalized": false,
|
| 108 |
+
"special": true
|
| 109 |
}
|
| 110 |
],
|
| 111 |
"normalizer": {
|
tokenizer_config.json
CHANGED
|
@@ -65,11 +65,37 @@
|
|
| 65 |
"rstrip": false,
|
| 66 |
"single_word": false,
|
| 67 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 68 |
}
|
| 69 |
},
|
| 70 |
"additional_special_tokens": [
|
| 71 |
-
"<|
|
| 72 |
-
"<|
|
|
|
|
|
|
|
| 73 |
],
|
| 74 |
"bos_token": "<|bos|>",
|
| 75 |
"clean_up_tokenization_spaces": false,
|
|
|
|
| 65 |
"rstrip": false,
|
| 66 |
"single_word": false,
|
| 67 |
"special": true
|
| 68 |
+
},
|
| 69 |
+
"32005": {
|
| 70 |
+
"content": "<|user|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"32006": {
|
| 78 |
+
"content": "<|assistant|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"32007": {
|
| 86 |
+
"content": "<|system|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
}
|
| 93 |
},
|
| 94 |
"additional_special_tokens": [
|
| 95 |
+
"<|user|>",
|
| 96 |
+
"<|assistant|>",
|
| 97 |
+
"<|system|>",
|
| 98 |
+
"<|endoftext|>"
|
| 99 |
],
|
| 100 |
"bos_token": "<|bos|>",
|
| 101 |
"clean_up_tokenization_spaces": false,
|