Tverous commited on
Commit
52753e4
1 Parent(s): fb4253c

commit files to HF hub

Browse files
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "MoritzLaurer/DeBERTa-v3-base-mnli-fever-anli",
3
  "architectures": [
4
  "DebertaV2ForSequenceClassification"
5
  ],
@@ -15,14 +15,14 @@
15
  },
16
  "hidden_act": "gelu",
17
  "hidden_dropout_prob": 0.1,
18
- "hidden_size": 768,
19
  "id2label": {
20
  "0": "entailment",
21
  "1": "neutral",
22
  "2": "contradiction"
23
  },
24
  "initializer_range": 0.02,
25
- "intermediate_size": 3072,
26
  "label2id": {
27
  "contradiction": 2,
28
  "entailment": 0,
@@ -33,12 +33,12 @@
33
  "max_relative_positions": -1,
34
  "model_type": "deberta-v2",
35
  "norm_rel_ebd": "layer_norm",
36
- "num_attention_heads": 12,
37
- "num_hidden_layers": 12,
38
  "pad_token_id": 0,
39
  "pooler_dropout": 0,
40
  "pooler_hidden_act": "gelu",
41
- "pooler_hidden_size": 768,
42
  "pos_att_type": [
43
  "p2c",
44
  "c2p"
@@ -48,7 +48,7 @@
48
  "relative_attention": true,
49
  "share_att_key": true,
50
  "torch_dtype": "float32",
51
- "transformers_version": "4.30.2",
52
  "type_vocab_size": 0,
53
  "vocab_size": 128100
54
  }
 
1
  {
2
+ "_name_or_path": "MoritzLaurer/DeBERTa-v3-large-mnli-fever-anli-ling-wanli",
3
  "architectures": [
4
  "DebertaV2ForSequenceClassification"
5
  ],
 
15
  },
16
  "hidden_act": "gelu",
17
  "hidden_dropout_prob": 0.1,
18
+ "hidden_size": 1024,
19
  "id2label": {
20
  "0": "entailment",
21
  "1": "neutral",
22
  "2": "contradiction"
23
  },
24
  "initializer_range": 0.02,
25
+ "intermediate_size": 4096,
26
  "label2id": {
27
  "contradiction": 2,
28
  "entailment": 0,
 
33
  "max_relative_positions": -1,
34
  "model_type": "deberta-v2",
35
  "norm_rel_ebd": "layer_norm",
36
+ "num_attention_heads": 16,
37
+ "num_hidden_layers": 24,
38
  "pad_token_id": 0,
39
  "pooler_dropout": 0,
40
  "pooler_hidden_act": "gelu",
41
+ "pooler_hidden_size": 1024,
42
  "pos_att_type": [
43
  "p2c",
44
  "c2p"
 
48
  "relative_attention": true,
49
  "share_att_key": true,
50
  "torch_dtype": "float32",
51
+ "transformers_version": "4.39.3",
52
  "type_vocab_size": 0,
53
  "vocab_size": 128100
54
  }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d4c8f6b3f29a0f6e44f4c2f69089e4e28506ead73a3128059cbf638a1c3df6c
3
+ size 1740308548
special_tokens_map.json CHANGED
@@ -1,9 +1,51 @@
1
  {
2
- "bos_token": "[CLS]",
3
- "cls_token": "[CLS]",
4
- "eos_token": "[SEP]",
5
- "mask_token": "[MASK]",
6
- "pad_token": "[PAD]",
7
- "sep_token": "[SEP]",
8
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,16 +1,62 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": "[CLS]",
3
  "clean_up_tokenization_spaces": true,
4
  "cls_token": "[CLS]",
5
  "do_lower_case": false,
6
  "eos_token": "[SEP]",
7
  "mask_token": "[MASK]",
 
8
  "model_max_length": 512,
9
  "pad_token": "[PAD]",
10
  "sep_token": "[SEP]",
11
  "sp_model_kwargs": {},
12
  "split_by_punct": false,
 
13
  "tokenizer_class": "DebertaV2Tokenizer",
 
 
14
  "unk_token": "[UNK]",
15
  "vocab_type": "spm"
16
  }
 
1
  {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
  "bos_token": "[CLS]",
45
  "clean_up_tokenization_spaces": true,
46
  "cls_token": "[CLS]",
47
  "do_lower_case": false,
48
  "eos_token": "[SEP]",
49
  "mask_token": "[MASK]",
50
+ "max_length": 512,
51
  "model_max_length": 512,
52
  "pad_token": "[PAD]",
53
  "sep_token": "[SEP]",
54
  "sp_model_kwargs": {},
55
  "split_by_punct": false,
56
+ "stride": 0,
57
  "tokenizer_class": "DebertaV2Tokenizer",
58
+ "truncation_side": "right",
59
+ "truncation_strategy": "longest_first",
60
  "unk_token": "[UNK]",
61
  "vocab_type": "spm"
62
  }