Hugging Face's logo

canwenxu
/
BERT-of-Theseus-MNLI

Feature Extraction
Transformers
PyTorch
JAX
bert
Inference Endpoints
Model card Files Community
1
system HF staff commited on
Commit
fc22c99
•
1 Parent(s): 04ade0e

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +47 -49
config.json CHANGED
@@ -1,49 +1,47 @@
1
- {
2
- "architectures": [
3
- "BertModel"
4
- ],
5
- "attention_probs_dropout_prob": 0.1,
6
- "bos_token_id": 0,
7
- "do_sample": false,
8
- "eos_token_ids": 0,
9
- "finetuning_task": "mnli",
10
- "hidden_act": "gelu",
11
- "hidden_dropout_prob": 0.1,
12
- "hidden_size": 768,
13
- "id2label": {
14
- "0": "LABEL_0",
15
- "1": "LABEL_1",
16
- "2": "LABEL_2"
17
- },
18
- "initializer_range": 0.02,
19
- "intermediate_size": 3072,
20
- "is_decoder": false,
21
- "label2id": {
22
- "LABEL_0": 0,
23
- "LABEL_1": 1,
24
- "LABEL_2": 2
25
- },
26
- "layer_norm_eps": 1e-12,
27
- "length_penalty": 1.0,
28
- "max_length": 20,
29
- "max_position_embeddings": 512,
30
- "model_type": "bert",
31
- "num_attention_heads": 12,
32
- "num_beams": 1,
33
- "num_hidden_layers": 6,
34
- "num_labels": 3,
35
- "num_return_sequences": 1,
36
- "output_attentions": false,
37
- "output_hidden_states": true,
38
- "output_past": true,
39
- "pad_token_id": 0,
40
- "pruned_heads": {},
41
- "repetition_penalty": 1.0,
42
- "temperature": 1.0,
43
- "top_k": 50,
44
- "top_p": 1.0,
45
- "torchscript": false,
46
- "type_vocab_size": 2,
47
- "use_bfloat16": false,
48
- "vocab_size": 30522
49
- }
1
+ {
2
+ "architectures": [
3
+ "BertModel"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "do_sample": false,
7
+ "finetuning_task": "mnli",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "is_decoder": false,
19
+ "label2id": {
20
+ "LABEL_0": 0,
21
+ "LABEL_1": 1,
22
+ "LABEL_2": 2
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "length_penalty": 1.0,
26
+ "max_length": 20,
27
+ "max_position_embeddings": 512,
28
+ "model_type": "bert",
29
+ "num_attention_heads": 12,
30
+ "num_beams": 1,
31
+ "num_hidden_layers": 6,
32
+ "num_labels": 3,
33
+ "num_return_sequences": 1,
34
+ "output_attentions": false,
35
+ "output_hidden_states": true,
36
+ "output_past": true,
37
+ "pad_token_id": 0,
38
+ "pruned_heads": {},
39
+ "repetition_penalty": 1.0,
40
+ "temperature": 1.0,
41
+ "top_k": 50,
42
+ "top_p": 1.0,
43
+ "torchscript": false,
44
+ "type_vocab_size": 2,
45
+ "use_bfloat16": false,
46
+ "vocab_size": 30522
47
+ }