Gajanan Deshmukh commited on
Upload tokenizer
Browse files- .gitattributes +1 -0
- tokenizer.json +3 -0
- tokenizer_config.json +13 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d7495baffd9d66f2b8010b65ec44e5504e0fd62ad3845cf565feee2b315adbe
|
| 3 |
+
size 27868275
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"is_local": false,
|
| 5 |
+
"local_files_only": false,
|
| 6 |
+
"model_input_names": [
|
| 7 |
+
"input_ids",
|
| 8 |
+
"attention_mask"
|
| 9 |
+
],
|
| 10 |
+
"model_max_length": 128000,
|
| 11 |
+
"pad_token": "<|endoftext|>",
|
| 12 |
+
"tokenizer_class": "TokenizersBackend"
|
| 13 |
+
}
|