l3cube-pune
commited on
Commit
•
c68aaab
1
Parent(s):
0dd089f
Update model files
Browse files- config.json +1 -1
- pytorch_model.bin +1 -1
- tokenizer.json +2 -2
- tokenizer_config.json +7 -4
- vocab.txt +0 -0
config.json
CHANGED
@@ -18,7 +18,7 @@
|
|
18 |
"pad_token_id": 0,
|
19 |
"position_embedding_type": "absolute",
|
20 |
"torch_dtype": "float32",
|
21 |
-
"transformers_version": "4.
|
22 |
"type_vocab_size": 2,
|
23 |
"use_cache": true,
|
24 |
"vocab_size": 100001
|
|
|
18 |
"pad_token_id": 0,
|
19 |
"position_embedding_type": "absolute",
|
20 |
"torch_dtype": "float32",
|
21 |
+
"transformers_version": "4.22.2",
|
22 |
"type_vocab_size": 2,
|
23 |
"use_cache": true,
|
24 |
"vocab_size": 100001
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 651843371
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96cbff2b6d425df20fd0c89526bf92c623c15bcbc2abbd177c0290114f829424
|
3 |
size 651843371
|
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 sha256:29db45b3ec0fa774065ed9e3e9ae6882f023a74469da34e3ac9bf5e14844f34a
|
3 |
+
size 3386586
|
tokenizer_config.json
CHANGED
@@ -1,12 +1,15 @@
|
|
1 |
{
|
2 |
"cls_token": "[CLS]",
|
|
|
|
|
3 |
"mask_token": "[MASK]",
|
4 |
-
"model_max_length": 512,
|
5 |
"name_or_path": "l3cube-pune/hindi-marathi-dev-bert-scratch",
|
|
|
6 |
"pad_token": "[PAD]",
|
7 |
-
"padding_side": "right",
|
8 |
"sep_token": "[SEP]",
|
9 |
-
"special_tokens_map_file": "
|
10 |
-
"
|
|
|
|
|
11 |
"unk_token": "[UNK]"
|
12 |
}
|
|
|
1 |
{
|
2 |
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": true,
|
5 |
"mask_token": "[MASK]",
|
|
|
6 |
"name_or_path": "l3cube-pune/hindi-marathi-dev-bert-scratch",
|
7 |
+
"never_split": null,
|
8 |
"pad_token": "[PAD]",
|
|
|
9 |
"sep_token": "[SEP]",
|
10 |
+
"special_tokens_map_file": "/ebs_ds_share/raviraj.j/temp/tokenizer/dev/special_tokens_map.json",
|
11 |
+
"strip_accents": null,
|
12 |
+
"tokenize_chinese_chars": true,
|
13 |
+
"tokenizer_class": "BertTokenizer",
|
14 |
"unk_token": "[UNK]"
|
15 |
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|