transZ commited on
Commit
927924f
1 Parent(s): d311c32

Upload ParExGenerator

Browse files
Files changed (3) hide show
  1. config.json +77 -0
  2. generation_config.json +13 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "v1",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "ParExGenerator"
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_bos_token_id": 0,
28
+ "forced_eos_token_id": 2,
29
+ "generate_input_dim": 768,
30
+ "gradient_checkpointing": false,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1",
34
+ "2": "LABEL_2"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_encoder_decoder": true,
38
+ "keyword_output_dim": 384,
39
+ "label2id": {
40
+ "LABEL_0": 0,
41
+ "LABEL_1": 1,
42
+ "LABEL_2": 2
43
+ },
44
+ "max_position_embeddings": 1024,
45
+ "model_type": "parex",
46
+ "no_repeat_ngram_size": 3,
47
+ "normalize_before": false,
48
+ "normalize_embedding": true,
49
+ "num_beams": 4,
50
+ "num_hidden_layers": 6,
51
+ "pad_token_id": 1,
52
+ "scale_embedding": false,
53
+ "task_specific_params": {
54
+ "summarization": {
55
+ "length_penalty": 1.0,
56
+ "max_length": 128,
57
+ "min_length": 12,
58
+ "num_beams": 4
59
+ },
60
+ "summarization_cnn": {
61
+ "length_penalty": 2.0,
62
+ "max_length": 142,
63
+ "min_length": 56,
64
+ "num_beams": 4
65
+ },
66
+ "summarization_xsum": {
67
+ "length_penalty": 1.0,
68
+ "max_length": 62,
69
+ "min_length": 11,
70
+ "num_beams": 6
71
+ }
72
+ },
73
+ "torch_dtype": "float32",
74
+ "transformers_version": "4.26.1",
75
+ "use_cache": true,
76
+ "vocab_size": 50267
77
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "early_stopping": true,
6
+ "eos_token_id": 2,
7
+ "forced_bos_token_id": 0,
8
+ "forced_eos_token_id": 2,
9
+ "no_repeat_ngram_size": 3,
10
+ "num_beams": 4,
11
+ "pad_token_id": 1,
12
+ "transformers_version": "4.26.1"
13
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32aff3f55d1282b2d765c39b01bebea7be7f2df571c0c44e965d62a99b0a11ac
3
+ size 713577449