Try to fix tokenizer
Browse files- special_tokens_map.json +7 -10
- tokenizer.json +0 -0
special_tokens_map.json
CHANGED
|
@@ -1,11 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"additional_special_tokens": [
|
| 3 |
-
"<|prompter|>",
|
| 4 |
-
"<|system|>",
|
| 5 |
-
"<|prefix_begin|>",
|
| 6 |
-
"<|prefix_end|>",
|
| 7 |
-
"<|assistant|>"
|
| 8 |
-
],
|
| 9 |
"bos_token": {
|
| 10 |
"content": "",
|
| 11 |
"lstrip": false,
|
|
@@ -13,9 +6,13 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
-
"eos_token":
|
| 17 |
-
|
| 18 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
"unk_token": {
|
| 20 |
"content": "",
|
| 21 |
"lstrip": false,
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": {
|
| 3 |
"content": "",
|
| 4 |
"lstrip": false,
|
|
|
|
| 6 |
"rstrip": false,
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
"unk_token": {
|
| 17 |
"content": "",
|
| 18 |
"lstrip": false,
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|