Upload tokenizer
Browse files- special_tokens_map.json +18 -6
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
special_tokens_map.json
CHANGED
|
@@ -1,24 +1,36 @@
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
-
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
],
|
| 6 |
"bos_token": {
|
| 7 |
-
"content": "
|
| 8 |
"lstrip": false,
|
| 9 |
"normalized": false,
|
| 10 |
"rstrip": false,
|
| 11 |
"single_word": false
|
| 12 |
},
|
| 13 |
"eos_token": {
|
| 14 |
-
"content": "
|
| 15 |
"lstrip": false,
|
| 16 |
"normalized": false,
|
| 17 |
"rstrip": false,
|
| 18 |
"single_word": false
|
| 19 |
},
|
| 20 |
-
"
|
| 21 |
-
"content": "
|
| 22 |
"lstrip": false,
|
| 23 |
"normalized": false,
|
| 24 |
"rstrip": false,
|
|
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<|Assistant|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "<|User|>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
}
|
| 17 |
],
|
| 18 |
"bos_token": {
|
| 19 |
+
"content": "<s>",
|
| 20 |
"lstrip": false,
|
| 21 |
"normalized": false,
|
| 22 |
"rstrip": false,
|
| 23 |
"single_word": false
|
| 24 |
},
|
| 25 |
"eos_token": {
|
| 26 |
+
"content": "</s>",
|
| 27 |
"lstrip": false,
|
| 28 |
"normalized": false,
|
| 29 |
"rstrip": false,
|
| 30 |
"single_word": false
|
| 31 |
},
|
| 32 |
+
"unk_token": {
|
| 33 |
+
"content": "<unk>",
|
| 34 |
"lstrip": false,
|
| 35 |
"normalized": false,
|
| 36 |
"rstrip": false,
|
tokenizer.json
CHANGED
|
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
|
|
|