Upload tokenizer
Browse files- special_tokens_map.json +3 -20
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
special_tokens_map.json
CHANGED
|
@@ -1,37 +1,20 @@
|
|
| 1 |
{
|
| 2 |
-
"additional_special_tokens": [
|
| 3 |
-
"<|im_end|>",
|
| 4 |
-
"<|im_user|>",
|
| 5 |
-
"<|im_assistant|>",
|
| 6 |
-
"<|start_header_id|>",
|
| 7 |
-
"<|end_header_id|>",
|
| 8 |
-
"[EOT]",
|
| 9 |
-
"<|im_system|>",
|
| 10 |
-
"<|im_middle|>"
|
| 11 |
-
],
|
| 12 |
"bos_token": {
|
| 13 |
-
"content": "
|
| 14 |
"lstrip": false,
|
| 15 |
"normalized": false,
|
| 16 |
"rstrip": false,
|
| 17 |
"single_word": false
|
| 18 |
},
|
| 19 |
"eos_token": {
|
| 20 |
-
"content": "
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": false,
|
| 23 |
"rstrip": false,
|
| 24 |
"single_word": false
|
| 25 |
},
|
| 26 |
"pad_token": {
|
| 27 |
-
"content": "
|
| 28 |
-
"lstrip": false,
|
| 29 |
-
"normalized": false,
|
| 30 |
-
"rstrip": false,
|
| 31 |
-
"single_word": false
|
| 32 |
-
},
|
| 33 |
-
"unk_token": {
|
| 34 |
-
"content": "[UNK]",
|
| 35 |
"lstrip": false,
|
| 36 |
"normalized": false,
|
| 37 |
"rstrip": false,
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
"lstrip": false,
|
| 5 |
"normalized": false,
|
| 6 |
"rstrip": false,
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
"rstrip": false,
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|