Sta-1 commited on
Commit
7f0e9e5
·
verified ·
1 Parent(s): e972440

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +57 -52
config.json CHANGED
@@ -1,52 +1,57 @@
1
- {
2
- "_name_or_path": "./my_local_model",
3
- "_num_labels": 3,
4
- "activation_dropout": 0.0,
5
- "activation_function": "gelu",
6
- "add_final_layer_norm": false,
7
- "architectures": [
8
- "BartForSequenceClassification"
9
- ],
10
- "attention_dropout": 0.0,
11
- "bos_token_id": 0,
12
- "classif_dropout": 0.0,
13
- "classifier_dropout": 0.0,
14
- "d_model": 1024,
15
- "decoder_attention_heads": 16,
16
- "decoder_ffn_dim": 4096,
17
- "decoder_layerdrop": 0.0,
18
- "decoder_layers": 12,
19
- "decoder_start_token_id": 2,
20
- "dropout": 0.1,
21
- "encoder_attention_heads": 16,
22
- "encoder_ffn_dim": 4096,
23
- "encoder_layerdrop": 0.0,
24
- "encoder_layers": 12,
25
- "eos_token_id": 2,
26
- "forced_eos_token_id": 2,
27
- "gradient_checkpointing": false,
28
- "id2label": {
29
- "0": "contradiction",
30
- "1": "neutral",
31
- "2": "entailment"
32
- },
33
- "init_std": 0.02,
34
- "is_encoder_decoder": true,
35
- "label2id": {
36
- "contradiction": 0,
37
- "entailment": 2,
38
- "neutral": 1
39
- },
40
- "max_position_embeddings": 1024,
41
- "model_type": "bart",
42
- "normalize_before": false,
43
- "num_hidden_layers": 12,
44
- "output_past": false,
45
- "pad_token_id": 1,
46
- "problem_type": "single_label_classification",
47
- "scale_embedding": false,
48
- "torch_dtype": "float32",
49
- "transformers_version": "4.49.0",
50
- "use_cache": true,
51
- "vocab_size": 50265
52
- }
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./my_local_model",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "gelu",
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForSequenceClassification"
9
+ ],
10
+ "model_type": "bart",
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 0,
13
+ "classif_dropout": 0.0,
14
+ "classifier_dropout": 0.0,
15
+ "d_model": 1024,
16
+ "decoder_attention_heads": 16,
17
+ "decoder_ffn_dim": 4096,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 12,
20
+ "decoder_start_token_id": 2,
21
+ "dropout": 0.1,
22
+ "encoder_attention_heads": 16,
23
+ "encoder_ffn_dim": 4096,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 12,
26
+ "eos_token_id": 2,
27
+ "forced_eos_token_id": 2,
28
+ "gradient_checkpointing": false,
29
+ "id2label": {
30
+ "0": "contradiction",
31
+ "1": "neutral",
32
+ "2": "entailment"
33
+ },
34
+ "init_std": 0.02,
35
+ "is_encoder_decoder": true,
36
+ "label2id": {
37
+ "contradiction": 0,
38
+ "entailment": 2,
39
+ "neutral": 1
40
+ },
41
+ "max_position_embeddings": 1024,
42
+ "model_type": "bart",
43
+ "normalize_before": false,
44
+ "num_hidden_layers": 12,
45
+ "output_past": false,
46
+ "pad_token_id": 1,
47
+ "problem_type": "single_label_classification",
48
+ "scale_embedding": false,
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.49.0",
51
+ "use_cache": true,
52
+ "vocab_size": 50265,
53
+ "pipeline_tag": "zero-shot-classification",
54
+ "auto_map": {
55
+ "AutoModelForSequenceClassification": "modeling_bart.BartForSequenceClassification"
56
+ }
57
+ }