Hugging Face's logo

eclec
/
patentClassfication3

Text Classification
Transformers
PyTorch
longformer
Generated from Trainer
Inference Endpoints
Model card Files Community
2
eclec commited on
Commit
327bd92
•
1 Parent(s): ee9e21c

Training in progress, epoch 1

Browse files
Files changed (8) hide show
  1. config.json +45 -15
  2. merges.txt +0 -0
  3. pytorch_model.bin +2 -2
  4. special_tokens_map.json +13 -5
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +12 -12
  7. training_args.bin +1 -1
  8. vocab.json +0 -0
config.json CHANGED
@@ -1,34 +1,64 @@
1
  {
2
- "_name_or_path": "allenai/scibert_scivocab_uncased",
3
  "architectures": [
4
- "BertForSequenceClassification"
5
  ],
 
6
  "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  "hidden_act": "gelu",
9
  "hidden_dropout_prob": 0.1,
10
- "hidden_size": 768,
11
  "id2label": {
12
  "0": "NOT_REJECTED",
13
  "1": "REJECTED"
14
  },
 
15
  "initializer_range": 0.02,
16
- "intermediate_size": 3072,
17
  "label2id": {
18
  "NOT_REJECTED": 0,
19
  "REJECTED": 1
20
  },
21
- "layer_norm_eps": 1e-12,
22
- "max_position_embeddings": 512,
23
- "model_type": "bert",
24
- "num_attention_heads": 12,
25
- "num_hidden_layers": 12,
26
- "pad_token_id": 0,
27
- "position_embedding_type": "absolute",
28
  "problem_type": "single_label_classification",
 
29
  "torch_dtype": "float32",
30
  "transformers_version": "4.31.0",
31
- "type_vocab_size": 2,
32
- "use_cache": true,
33
- "vocab_size": 31090
34
  }
 
1
  {
2
+ "_name_or_path": "allenai/longformer-large-4096",
3
  "architectures": [
4
+ "LongformerForSequenceClassification"
5
  ],
6
+ "attention_mode": "longformer",
7
  "attention_probs_dropout_prob": 0.1,
8
+ "attention_window": [
9
+ 512,
10
+ 512,
11
+ 512,
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512,
26
+ 512,
27
+ 512,
28
+ 512,
29
+ 512,
30
+ 512,
31
+ 512,
32
+ 512
33
+ ],
34
+ "bos_token_id": 0,
35
+ "eos_token_id": 2,
36
+ "gradient_checkpointing": false,
37
  "hidden_act": "gelu",
38
  "hidden_dropout_prob": 0.1,
39
+ "hidden_size": 1024,
40
  "id2label": {
41
  "0": "NOT_REJECTED",
42
  "1": "REJECTED"
43
  },
44
+ "ignore_attention_mask": false,
45
  "initializer_range": 0.02,
46
+ "intermediate_size": 4096,
47
  "label2id": {
48
  "NOT_REJECTED": 0,
49
  "REJECTED": 1
50
  },
51
+ "layer_norm_eps": 1e-05,
52
+ "max_position_embeddings": 4098,
53
+ "model_type": "longformer",
54
+ "num_attention_heads": 16,
55
+ "num_hidden_layers": 24,
56
+ "onnx_export": false,
57
+ "pad_token_id": 1,
58
  "problem_type": "single_label_classification",
59
+ "sep_token_id": 2,
60
  "torch_dtype": "float32",
61
  "transformers_version": "4.31.0",
62
+ "type_vocab_size": 1,
63
+ "vocab_size": 50265
 
64
  }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:835dd9a27fd4e49da124765542a86beb00dedd12a61d607f7a7848e037f72997
3
- size 439748401
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68398b234cdab12b3591b8afeb4aad71061f467e563c2ee8bcc20d1b9d5cf05d
3
+ size 1738600369
special_tokens_map.json CHANGED
@@ -1,7 +1,15 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
7
  }
 
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
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,15 +1,15 @@
1
  {
 
 
2
  "clean_up_tokenization_spaces": true,
3
- "cls_token": "[CLS]",
4
- "do_basic_tokenize": true,
5
- "do_lower_case": true,
6
- "mask_token": "[MASK]",
7
- "model_max_length": 512,
8
- "never_split": null,
9
- "pad_token": "[PAD]",
10
- "sep_token": "[SEP]",
11
- "strip_accents": null,
12
- "tokenize_chinese_chars": true,
13
- "tokenizer_class": "BertTokenizer",
14
- "unk_token": "[UNK]"
15
  }
 
1
  {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
  "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "mask_token": "<mask>",
9
+ "model_max_length": 4096,
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "tokenizer_class": "LongformerTokenizer",
13
+ "trim_offsets": true,
14
+ "unk_token": "<unk>"
 
 
15
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4631d240a15ad5fa0bcd7e62886e0d38613c687d5d73f3e35caa90d0c35f039
3
  size 3963
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9567677662a5b37852c94b194c9efb6a1bdf98f9445b8fdc8285ac129fa27464
3
  size 3963
vocab.json ADDED
The diff for this file is too large to render. See raw diff