Upload tokenizer
Browse files- special_tokens_map.json +1 -1
- tokenizer.json +2 -2
- tokenizer_config.json +1 -2
special_tokens_map.json
CHANGED
|
@@ -22,7 +22,7 @@
|
|
| 22 |
"single_word": false
|
| 23 |
},
|
| 24 |
"pad_token": {
|
| 25 |
-
"content": "<|
|
| 26 |
"lstrip": false,
|
| 27 |
"normalized": false,
|
| 28 |
"rstrip": false,
|
|
|
|
| 22 |
"single_word": false
|
| 23 |
},
|
| 24 |
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
"lstrip": false,
|
| 27 |
"normalized": false,
|
| 28 |
"rstrip": false,
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
CHANGED
|
@@ -232,8 +232,7 @@
|
|
| 232 |
"errors": "replace",
|
| 233 |
"extra_special_tokens": {},
|
| 234 |
"model_max_length": 262144,
|
| 235 |
-
"pad_token": "<|
|
| 236 |
-
"padding_side": "left",
|
| 237 |
"split_special_tokens": false,
|
| 238 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 239 |
"unk_token": null
|
|
|
|
| 232 |
"errors": "replace",
|
| 233 |
"extra_special_tokens": {},
|
| 234 |
"model_max_length": 262144,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
|
|
|
| 236 |
"split_special_tokens": false,
|
| 237 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 238 |
"unk_token": null
|