Hugging Face's logo

eclec
/
patentClassfication2

Text Classification
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
eclec commited on
Commit
5990238
•
1 Parent(s): 21dc9e1

Training in progress, epoch 1

Browse files
Files changed (6) hide show
  1. config.json +16 -15
  2. pytorch_model.bin +2 -2
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +3 -1
  5. training_args.bin +1 -1
  6. vocab.txt +0 -0
config.json CHANGED
@@ -1,33 +1,34 @@
1
  {
2
- "_name_or_path": "distilbert-base-uncased",
3
- "activation": "gelu",
4
  "architectures": [
5
- "DistilBertForSequenceClassification"
6
  ],
7
- "attention_dropout": 0.1,
8
- "dim": 768,
9
- "dropout": 0.1,
10
- "hidden_dim": 3072,
 
11
  "id2label": {
12
  "0": "NOT_REJECTED",
13
  "1": "REJECTED"
14
  },
15
  "initializer_range": 0.02,
 
16
  "label2id": {
17
  "NOT_REJECTED": 0,
18
  "REJECTED": 1
19
  },
 
20
  "max_position_embeddings": 512,
21
- "model_type": "distilbert",
22
- "n_heads": 12,
23
- "n_layers": 6,
24
  "pad_token_id": 0,
 
25
  "problem_type": "single_label_classification",
26
- "qa_dropout": 0.1,
27
- "seq_classif_dropout": 0.2,
28
- "sinusoidal_pos_embds": false,
29
- "tie_weights_": true,
30
  "torch_dtype": "float32",
31
  "transformers_version": "4.31.0",
32
- "vocab_size": 30522
 
 
33
  }
 
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
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:779841cb258d4e622f3d875f26a7114b0a1d3a3b07d15222aa6a628b85550927
3
- size 267855533
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd8ea622bab0de9141014c59eaffa50579dec8c060e0f443d4a25ac01d1a0407
3
+ size 439748401
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,13 +1,15 @@
1
  {
2
  "clean_up_tokenization_spaces": true,
3
  "cls_token": "[CLS]",
 
4
  "do_lower_case": true,
5
  "mask_token": "[MASK]",
6
  "model_max_length": 512,
 
7
  "pad_token": "[PAD]",
8
  "sep_token": "[SEP]",
9
  "strip_accents": null,
10
  "tokenize_chinese_chars": true,
11
- "tokenizer_class": "DistilBertTokenizer",
12
  "unk_token": "[UNK]"
13
  }
 
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
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d8e866c93ba32c77d1bffd645b3a408ffe13ca5fe577a7fa9e3a09d49455ad0
3
  size 3963
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7f9005e78418379296e790215e4a0624730250c82f1b65c8e6eae611985d3ba
3
  size 3963
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff