SrikrishnaIyer commited on
Commit
49993b4
·
verified ·
1 Parent(s): 9e971f0

updated model files

Browse files
config.json CHANGED
@@ -1,7 +1,4 @@
1
  {
2
- "architectures": [
3
- "RobertaForMaskedLM"
4
- ],
5
  "attention_probs_dropout_prob": 0.1,
6
  "bos_token_id": 0,
7
  "classifier_dropout": null,
@@ -14,11 +11,10 @@
14
  "layer_norm_eps": 1e-12,
15
  "max_position_embeddings": 514,
16
  "model_type": "roberta",
17
- "num_attention_heads": 32,
18
  "num_hidden_layers": 32,
19
  "pad_token_id": 1,
20
  "position_embedding_type": "absolute",
21
- "torch_dtype": "float32",
22
  "transformers_version": "4.37.0",
23
  "type_vocab_size": 2,
24
  "use_cache": true,
 
1
  {
 
 
 
2
  "attention_probs_dropout_prob": 0.1,
3
  "bos_token_id": 0,
4
  "classifier_dropout": null,
 
11
  "layer_norm_eps": 1e-12,
12
  "max_position_embeddings": 514,
13
  "model_type": "roberta",
14
+ "num_attention_heads": 4,
15
  "num_hidden_layers": 32,
16
  "pad_token_id": 1,
17
  "position_embedding_type": "absolute",
 
18
  "transformers_version": "4.37.0",
19
  "type_vocab_size": 2,
20
  "use_cache": true,
merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa800ab4e97200542bfa5db649fdfd9a2fd3b3c7f157041d28ffe691abb37bd0
3
  size 135924052
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6ee6b903b94ce2039bf3f058ac98e8c0b6c6284d9fa5c4c857e33cf70eb0bc5
3
  size 135924052
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer_config.json CHANGED
@@ -61,4 +61,4 @@
61
  "rstrip": false,
62
  "single_word": false
63
  }
64
- }
 
61
  "rstrip": false,
62
  "single_word": false
63
  }
64
+ }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff