Commit
•
6f8ef97
1
Parent(s):
60efda3
Upload tokenizer
Browse files- special_tokens_map.json +14 -2
- tokenizer.json +0 -0
- vocab.json +0 -0
special_tokens_map.json
CHANGED
|
@@ -1,7 +1,19 @@
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
-
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
],
|
| 6 |
"bos_token": {
|
| 7 |
"content": "<|endoftext|>",
|
|
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<|im_start|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "<|im_end|>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
}
|
| 17 |
],
|
| 18 |
"bos_token": {
|
| 19 |
"content": "<|endoftext|>",
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|