woland2k commited on
Commit
a8e19e6
·
verified ·
1 Parent(s): 93df631

Upload 7 files

Browse files
config.json CHANGED
@@ -1,13 +1,14 @@
1
  {
2
- "_name_or_path": "microsoft/deberta-base",
 
3
  "architectures": [
4
- "DebertaForSequenceClassification"
5
  ],
6
- "attention_probs_dropout_prob": 0.1,
 
 
7
  "finetuning_task": "text-classification",
8
- "hidden_act": "gelu",
9
- "hidden_dropout_prob": 0.1,
10
- "hidden_size": 768,
11
  "id2label": {
12
  "0": "10111301",
13
  "1": "10111302",
@@ -3927,7 +3928,6 @@
3927
  "3915": "95141801"
3928
  },
3929
  "initializer_range": 0.02,
3930
- "intermediate_size": 3072,
3931
  "label2id": {
3932
  "10111301": 0,
3933
  "10111302": 1,
@@ -7846,25 +7846,17 @@
7846
  "95141705": 3914,
7847
  "95141801": 3915
7848
  },
7849
- "layer_norm_eps": 1e-07,
7850
  "max_position_embeddings": 512,
7851
- "max_relative_positions": -1,
7852
- "model_type": "deberta",
7853
- "num_attention_heads": 12,
7854
- "num_hidden_layers": 12,
7855
  "pad_token_id": 0,
7856
- "pooler_dropout": 0,
7857
- "pooler_hidden_act": "gelu",
7858
- "pooler_hidden_size": 768,
7859
- "pos_att_type": [
7860
- "c2p",
7861
- "p2c"
7862
- ],
7863
- "position_biased_input": false,
7864
  "problem_type": "single_label_classification",
7865
- "relative_attention": true,
 
 
 
7866
  "torch_dtype": "float32",
7867
- "transformers_version": "4.42.0.dev0",
7868
- "type_vocab_size": 0,
7869
- "vocab_size": 50265
7870
  }
 
1
  {
2
+ "_name_or_path": "distilbert/distilbert-base-uncased",
3
+ "activation": "gelu",
4
  "architectures": [
5
+ "DistilBertForSequenceClassification"
6
  ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
  "finetuning_task": "text-classification",
11
+ "hidden_dim": 3072,
 
 
12
  "id2label": {
13
  "0": "10111301",
14
  "1": "10111302",
 
3928
  "3915": "95141801"
3929
  },
3930
  "initializer_range": 0.02,
 
3931
  "label2id": {
3932
  "10111301": 0,
3933
  "10111302": 1,
 
7846
  "95141705": 3914,
7847
  "95141801": 3915
7848
  },
 
7849
  "max_position_embeddings": 512,
7850
+ "model_type": "distilbert",
7851
+ "n_heads": 12,
7852
+ "n_layers": 6,
 
7853
  "pad_token_id": 0,
 
 
 
 
 
 
 
 
7854
  "problem_type": "single_label_classification",
7855
+ "qa_dropout": 0.1,
7856
+ "seq_classif_dropout": 0.2,
7857
+ "sinusoidal_pos_embds": false,
7858
+ "tie_weights_": true,
7859
  "torch_dtype": "float32",
7860
+ "transformers_version": "4.41.0",
7861
+ "vocab_size": 30522
 
7862
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08662a4197ef5df43240690b24fc95c45a5f5d764e419586e45d681e970c1007
3
- size 568839064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e5698a825377885b2ad3346e3d66ad78263ef4499771448d1dc6e04074ad779
3
+ size 279872072
special_tokens_map.json CHANGED
@@ -1,51 +1,7 @@
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": true,
26
- "normalized": true,
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
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,6 +1,4 @@
1
  {
2
- "add_bos_token": false,
3
- "add_prefix_space": false,
4
  "added_tokens_decoder": {
5
  "0": {
6
  "content": "[PAD]",
@@ -10,50 +8,48 @@
10
  "single_word": false,
11
  "special": true
12
  },
13
- "1": {
14
- "content": "[CLS]",
15
  "lstrip": false,
16
  "normalized": false,
17
  "rstrip": false,
18
  "single_word": false,
19
  "special": true
20
  },
21
- "2": {
22
- "content": "[SEP]",
23
  "lstrip": false,
24
  "normalized": false,
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
28
  },
29
- "3": {
30
- "content": "[UNK]",
31
  "lstrip": false,
32
  "normalized": false,
33
  "rstrip": false,
34
  "single_word": false,
35
  "special": true
36
  },
37
- "50264": {
38
  "content": "[MASK]",
39
- "lstrip": true,
40
- "normalized": true,
41
  "rstrip": false,
42
  "single_word": false,
43
  "special": true
44
  }
45
  },
46
- "bos_token": "[CLS]",
47
  "clean_up_tokenization_spaces": true,
48
  "cls_token": "[CLS]",
49
- "do_lower_case": false,
50
- "eos_token": "[SEP]",
51
- "errors": "replace",
52
  "mask_token": "[MASK]",
53
- "model_max_length": 1000000000000000019884624838656,
54
  "pad_token": "[PAD]",
55
  "sep_token": "[SEP]",
56
- "tokenizer_class": "DebertaTokenizer",
57
- "unk_token": "[UNK]",
58
- "vocab_type": "gpt2"
 
59
  }
 
1
  {
 
 
2
  "added_tokens_decoder": {
3
  "0": {
4
  "content": "[PAD]",
 
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "100": {
12
+ "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "101": {
20
+ "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "102": {
28
+ "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "103": {
36
  "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
  }
43
  },
 
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
+ "do_lower_case": true,
 
 
47
  "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
  "pad_token": "[PAD]",
50
  "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b553b095eadfd9ff500412d462ab5867e6651343991e0942df7b216d4e64f1d
3
- size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:561793464897e0c64f900683ac7465e9310ec4b4ac1fa9c5690fd8ef63a05f90
3
+ size 4667
vocab.txt ADDED
The diff for this file is too large to render. See raw diff