Hugging Face's logo

microsoft
/
tapex-base

Table Question Answering
Transformers
PyTorch
Safetensors
English
bart
text2text-generation
tapex
Model card Files Community
2
Qian Liu commited on
Commit
a1180b7
·
1 Parent(s): e195be4

Update activation dropout

Browse files
Files changed (1) hide show
  1. config.json +73 -74
config.json CHANGED
@@ -1,74 +1,73 @@
1
- {
2
- "_name_or_path": "tapex-base",
3
- "activation_dropout": 0.1,
4
- "activation_function": "gelu",
5
- "add_bias_logits": false,
6
- "add_final_layer_norm": false,
7
- "architectures": [
8
- "BartModel"
9
- ],
10
- "attention_dropout": 0.1,
11
- "bos_token_id": 0,
12
- "classif_dropout": 0.1,
13
- "classifier_dropout": 0.0,
14
- "d_model": 768,
15
- "decoder_attention_heads": 12,
16
- "decoder_ffn_dim": 3072,
17
- "decoder_layerdrop": 0.0,
18
- "decoder_layers": 6,
19
- "decoder_start_token_id": 2,
20
- "dropout": 0.1,
21
- "early_stopping": true,
22
- "encoder_attention_heads": 12,
23
- "encoder_ffn_dim": 3072,
24
- "encoder_layerdrop": 0.0,
25
- "encoder_layers": 6,
26
- "eos_token_id": 2,
27
- "forced_eos_token_id": 2,
28
- "gradient_checkpointing": false,
29
- "id2label": {
30
- "0": "LABEL_0",
31
- "1": "LABEL_1",
32
- "2": "LABEL_2"
33
- },
34
- "init_std": 0.02,
35
- "is_encoder_decoder": true,
36
- "label2id": {
37
- "LABEL_0": 0,
38
- "LABEL_1": 1,
39
- "LABEL_2": 2
40
- },
41
- "max_position_embeddings": 1024,
42
- "model_type": "bart",
43
- "no_repeat_ngram_size": 3,
44
- "normalize_before": false,
45
- "normalize_embedding": true,
46
- "num_beams": 4,
47
- "num_hidden_layers": 6,
48
- "pad_token_id": 1,
49
- "scale_embedding": false,
50
- "task_specific_params": {
51
- "summarization": {
52
- "length_penalty": 1.0,
53
- "max_length": 128,
54
- "min_length": 12,
55
- "num_beams": 4
56
- },
57
- "summarization_cnn": {
58
- "length_penalty": 2.0,
59
- "max_length": 142,
60
- "min_length": 56,
61
- "num_beams": 4
62
- },
63
- "summarization_xsum": {
64
- "length_penalty": 1.0,
65
- "max_length": 62,
66
- "min_length": 11,
67
- "num_beams": 6
68
- }
69
- },
70
- "torch_dtype": "float32",
71
- "transformers_version": "4.12.0.dev0",
72
- "use_cache": true,
73
- "vocab_size": 50265
74
- }
 
1
+ {
2
+ "_name_or_path": "bart-base",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartModel"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classifier_dropout": 0.0,
13
+ "d_model": 768,
14
+ "decoder_attention_heads": 12,
15
+ "decoder_ffn_dim": 3072,
16
+ "decoder_layerdrop": 0.0,
17
+ "decoder_layers": 6,
18
+ "decoder_start_token_id": 2,
19
+ "dropout": 0.1,
20
+ "early_stopping": true,
21
+ "encoder_attention_heads": 12,
22
+ "encoder_ffn_dim": 3072,
23
+ "encoder_layerdrop": 0.0,
24
+ "encoder_layers": 6,
25
+ "eos_token_id": 2,
26
+ "forced_eos_token_id": 2,
27
+ "gradient_checkpointing": false,
28
+ "id2label": {
29
+ "0": "LABEL_0",
30
+ "1": "LABEL_1",
31
+ "2": "LABEL_2"
32
+ },
33
+ "init_std": 0.02,
34
+ "is_encoder_decoder": true,
35
+ "label2id": {
36
+ "LABEL_0": 0,
37
+ "LABEL_1": 1,
38
+ "LABEL_2": 2
39
+ },
40
+ "max_position_embeddings": 1024,
41
+ "model_type": "bart",
42
+ "no_repeat_ngram_size": 3,
43
+ "normalize_before": false,
44
+ "normalize_embedding": true,
45
+ "num_beams": 4,
46
+ "num_hidden_layers": 6,
47
+ "pad_token_id": 1,
48
+ "scale_embedding": false,
49
+ "task_specific_params": {
50
+ "summarization": {
51
+ "length_penalty": 1.0,
52
+ "max_length": 128,
53
+ "min_length": 12,
54
+ "num_beams": 4
55
+ },
56
+ "summarization_cnn": {
57
+ "length_penalty": 2.0,
58
+ "max_length": 142,
59
+ "min_length": 56,
60
+ "num_beams": 4
61
+ },
62
+ "summarization_xsum": {
63
+ "length_penalty": 1.0,
64
+ "max_length": 62,
65
+ "min_length": 11,
66
+ "num_beams": 6
67
+ }
68
+ },
69
+ "torch_dtype": "float32",
70
+ "transformers_version": "4.12.0.dev0",
71
+ "use_cache": true,
72
+ "vocab_size": 50265
73
+ }