Add v2023 model and tokenizer(BBPE)
Browse files- config.json +3 -3
- pytorch_model.bin +2 -2
- tokenizer.json +0 -0
- vocab.txt +0 -0
config.json
CHANGED
|
@@ -15,7 +15,7 @@
|
|
| 15 |
"max_position_embeddings": 512,
|
| 16 |
"model_type": "electra",
|
| 17 |
"type_vocab_size": 2,
|
| 18 |
-
"vocab_size":
|
| 19 |
-
"pad_token_id":
|
| 20 |
-
"tokenizer_class": "
|
| 21 |
}
|
|
|
|
| 15 |
"max_position_embeddings": 512,
|
| 16 |
"model_type": "electra",
|
| 17 |
"type_vocab_size": 2,
|
| 18 |
+
"vocab_size": 30000,
|
| 19 |
+
"pad_token_id": 3,
|
| 20 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 21 |
}
|
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:fb28c533dac6884c7eb6e6f8bc194e09a4cecf29f04b724fc85456055aa702d7
|
| 3 |
+
size 436413813
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
vocab.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|