Commit
•
bee7755
1
Parent(s):
e8f0bbe
Upload tokenizer
Browse files- special_tokens_map.json +1 -1
- tokenizer.json +3 -11
- tokenizer_config.json +0 -0
special_tokens_map.json
CHANGED
|
@@ -14,7 +14,7 @@
|
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"pad_token": {
|
| 17 |
-
"content": "
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
"rstrip": false,
|
|
|
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"pad_token": {
|
| 17 |
+
"content": "<|im_end|>",
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
"rstrip": false,
|
tokenizer.json
CHANGED
|
@@ -23,15 +23,6 @@
|
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"id": 2,
|
| 26 |
-
"content": "</s>",
|
| 27 |
-
"single_word": false,
|
| 28 |
-
"lstrip": false,
|
| 29 |
-
"rstrip": false,
|
| 30 |
-
"normalized": false,
|
| 31 |
-
"special": true
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"id": 32000,
|
| 35 |
"content": "<|im_end|>",
|
| 36 |
"single_word": false,
|
| 37 |
"lstrip": false,
|
|
@@ -40,7 +31,7 @@
|
|
| 40 |
"special": true
|
| 41 |
},
|
| 42 |
{
|
| 43 |
-
"id":
|
| 44 |
"content": "<|im_start|>",
|
| 45 |
"single_word": false,
|
| 46 |
"lstrip": false,
|
|
@@ -152,10 +143,11 @@
|
|
| 152 |
"end_of_word_suffix": null,
|
| 153 |
"fuse_unk": true,
|
| 154 |
"byte_fallback": true,
|
|
|
|
| 155 |
"vocab": {
|
| 156 |
"<unk>": 0,
|
| 157 |
"<s>": 1,
|
| 158 |
-
"
|
| 159 |
"<0x00>": 3,
|
| 160 |
"<0x01>": 4,
|
| 161 |
"<0x02>": 5,
|
|
|
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"id": 2,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
"content": "<|im_end|>",
|
| 27 |
"single_word": false,
|
| 28 |
"lstrip": false,
|
|
|
|
| 31 |
"special": true
|
| 32 |
},
|
| 33 |
{
|
| 34 |
+
"id": 32000,
|
| 35 |
"content": "<|im_start|>",
|
| 36 |
"single_word": false,
|
| 37 |
"lstrip": false,
|
|
|
|
| 143 |
"end_of_word_suffix": null,
|
| 144 |
"fuse_unk": true,
|
| 145 |
"byte_fallback": true,
|
| 146 |
+
"ignore_merges": false,
|
| 147 |
"vocab": {
|
| 148 |
"<unk>": 0,
|
| 149 |
"<s>": 1,
|
| 150 |
+
"<|im_end|>": 2,
|
| 151 |
"<0x00>": 3,
|
| 152 |
"<0x01>": 4,
|
| 153 |
"<0x02>": 5,
|
tokenizer_config.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|