l3cube-pune
commited on
Commit
•
63eaf85
1
Parent(s):
c577bf7
Update model files
Browse files- config.json +2 -2
- pytorch_model.bin +2 -2
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +1 -15
- tokenizer.json +2 -2
- tokenizer_config.json +1 -19
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"XLMRobertaForMaskedLM"
|
5 |
],
|
@@ -21,7 +21,7 @@
|
|
21 |
"pad_token_id": 1,
|
22 |
"position_embedding_type": "absolute",
|
23 |
"torch_dtype": "float32",
|
24 |
-
"transformers_version": "4.
|
25 |
"type_vocab_size": 1,
|
26 |
"use_cache": true,
|
27 |
"vocab_size": 250002
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/ebs_ds_share/raviraj.j/temp/dev_roberta/checkpoint-1632000/",
|
3 |
"architectures": [
|
4 |
"XLMRobertaForMaskedLM"
|
5 |
],
|
|
|
21 |
"pad_token_id": 1,
|
22 |
"position_embedding_type": "absolute",
|
23 |
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.15.0",
|
25 |
"type_vocab_size": 1,
|
26 |
"use_cache": true,
|
27 |
"vocab_size": 250002
|
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 sha256:82b183ef16392c08a3d31ca44463fb4d6d6adeec5b5618333a49694508d60353
|
3 |
+
size 1113268818
|
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
@@ -1,15 +1 @@
|
|
1 |
-
{
|
2 |
-
"bos_token": "<s>",
|
3 |
-
"cls_token": "<s>",
|
4 |
-
"eos_token": "</s>",
|
5 |
-
"mask_token": {
|
6 |
-
"content": "<mask>",
|
7 |
-
"lstrip": true,
|
8 |
-
"normalized": false,
|
9 |
-
"rstrip": false,
|
10 |
-
"single_word": false
|
11 |
-
},
|
12 |
-
"pad_token": "<pad>",
|
13 |
-
"sep_token": "</s>",
|
14 |
-
"unk_token": "<unk>"
|
15 |
-
}
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": 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 sha256:2a0d7366dd7780ea36cc42431dd74cd79289b783ab01acd33013fcc96865a8e9
|
3 |
+
size 9081351
|
tokenizer_config.json
CHANGED
@@ -1,19 +1 @@
|
|
1 |
-
{
|
2 |
-
"bos_token": "<s>",
|
3 |
-
"cls_token": "<s>",
|
4 |
-
"eos_token": "</s>",
|
5 |
-
"mask_token": {
|
6 |
-
"__type": "AddedToken",
|
7 |
-
"content": "<mask>",
|
8 |
-
"lstrip": true,
|
9 |
-
"normalized": true,
|
10 |
-
"rstrip": false,
|
11 |
-
"single_word": false
|
12 |
-
},
|
13 |
-
"name_or_path": "l3cube-pune/hindi-marathi-dev-roberta",
|
14 |
-
"pad_token": "<pad>",
|
15 |
-
"sep_token": "</s>",
|
16 |
-
"special_tokens_map_file": null,
|
17 |
-
"tokenizer_class": "XLMRobertaTokenizer",
|
18 |
-
"unk_token": "<unk>"
|
19 |
-
}
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "special_tokens_map_file": null, "name_or_path": "xlm-roberta-base/", "tokenizer_class": "XLMRobertaTokenizer"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|