Upload tiny models for XmodForMaskedLM
Browse files- .gitattributes +1 -0
- config.json +1 -1
- pytorch_model.bin +2 -2
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +1 -1
- tokenizer.json +0 -0
- tokenizer_config.json +2 -1
.gitattributes
CHANGED
|
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
CHANGED
|
@@ -31,5 +31,5 @@
|
|
| 31 |
"transformers_version": "4.28.0.dev0",
|
| 32 |
"type_vocab_size": 16,
|
| 33 |
"use_cache": true,
|
| 34 |
-
"vocab_size":
|
| 35 |
}
|
|
|
|
| 31 |
"transformers_version": "4.28.0.dev0",
|
| 32 |
"type_vocab_size": 16,
|
| 33 |
"use_cache": true,
|
| 34 |
+
"vocab_size": 250002
|
| 35 |
}
|
pytorch_model.bin
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 sha256:026fb71e266a23222200bc62ea8bf0160af1f85dd8e1b2c3d3e124932060f83e
|
| 3 |
+
size 33270025
|
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
| 3 |
+
size 5069051
|
special_tokens_map.json
CHANGED
|
@@ -5,7 +5,7 @@
|
|
| 5 |
"mask_token": {
|
| 6 |
"content": "<mask>",
|
| 7 |
"lstrip": true,
|
| 8 |
-
"normalized":
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
|
|
|
| 5 |
"mask_token": {
|
| 6 |
"content": "<mask>",
|
| 7 |
"lstrip": true,
|
| 8 |
+
"normalized": true,
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -6,13 +6,14 @@
|
|
| 6 |
"__type": "AddedToken",
|
| 7 |
"content": "<mask>",
|
| 8 |
"lstrip": true,
|
| 9 |
-
"normalized":
|
| 10 |
"rstrip": false,
|
| 11 |
"single_word": false
|
| 12 |
},
|
| 13 |
"model_max_length": 510,
|
| 14 |
"pad_token": "<pad>",
|
| 15 |
"sep_token": "</s>",
|
|
|
|
| 16 |
"special_tokens_map_file": null,
|
| 17 |
"tokenizer_class": "XLMRobertaTokenizer",
|
| 18 |
"unk_token": "<unk>"
|
|
|
|
| 6 |
"__type": "AddedToken",
|
| 7 |
"content": "<mask>",
|
| 8 |
"lstrip": true,
|
| 9 |
+
"normalized": true,
|
| 10 |
"rstrip": false,
|
| 11 |
"single_word": false
|
| 12 |
},
|
| 13 |
"model_max_length": 510,
|
| 14 |
"pad_token": "<pad>",
|
| 15 |
"sep_token": "</s>",
|
| 16 |
+
"sp_model_kwargs": {},
|
| 17 |
"special_tokens_map_file": null,
|
| 18 |
"tokenizer_class": "XLMRobertaTokenizer",
|
| 19 |
"unk_token": "<unk>"
|