peterandrew987 commited on
Commit
7f88000
1 Parent(s): 4dc730a

Upload MBartForConditionalGeneration

Browse files
Files changed (3) hide show
  1. config.json +94 -0
  2. generation_config.json +12 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "activation_function": "gelu",
4
+ "add_bias_logits": false,
5
+ "add_final_layer_norm": false,
6
+ "architectures": [
7
+ "MBartForConditionalGeneration"
8
+ ],
9
+ "attention_dilation": [
10
+ 1,
11
+ 1,
12
+ 1,
13
+ 1,
14
+ 1,
15
+ 1
16
+ ],
17
+ "attention_dropout": 0.1,
18
+ "attention_mode": "sliding_chunks",
19
+ "attention_probs_dropout_prob": 0.1,
20
+ "attention_window": [
21
+ 1024,
22
+ 1024,
23
+ 1024,
24
+ 1024,
25
+ 1024,
26
+ 1024
27
+ ],
28
+ "autoregressive": false,
29
+ "bos_token_id": 0,
30
+ "classif_dropout": 0.1,
31
+ "classifier_dropout": 0.0,
32
+ "d_model": 768,
33
+ "decoder_attention_heads": 12,
34
+ "decoder_ffn_dim": 3072,
35
+ "decoder_layerdrop": 0.0,
36
+ "decoder_layers": 6,
37
+ "decoder_start_token_id": 2,
38
+ "dropout": 0.1,
39
+ "early_stopping": true,
40
+ "encoder_attention_heads": 12,
41
+ "encoder_ffn_dim": 3072,
42
+ "encoder_layerdrop": 0.0,
43
+ "encoder_layers": 6,
44
+ "eos_token_id": 2,
45
+ "forced_eos_token_id": 2,
46
+ "gradient_checkpointing": false,
47
+ "id2label": {
48
+ "0": "LABEL_0",
49
+ "1": "LABEL_1",
50
+ "2": "LABEL_2"
51
+ },
52
+ "init_std": 0.02,
53
+ "is_encoder_decoder": true,
54
+ "label2id": {
55
+ "LABEL_0": 0,
56
+ "LABEL_1": 1,
57
+ "LABEL_2": 2
58
+ },
59
+ "max_decoder_position_embeddings": 1024,
60
+ "max_encoder_position_embeddings": 1024,
61
+ "model_type": "mbart",
62
+ "no_repeat_ngram_size": 3,
63
+ "normalize_before": false,
64
+ "normalize_embedding": true,
65
+ "num_beams": 4,
66
+ "num_hidden_layers": 6,
67
+ "pad_token_id": 1,
68
+ "scale_embedding": false,
69
+ "task_specific_params": {
70
+ "summarization": {
71
+ "length_penalty": 1.0,
72
+ "max_length": 128,
73
+ "min_length": 12,
74
+ "num_beams": 4
75
+ },
76
+ "summarization_cnn": {
77
+ "length_penalty": 2.0,
78
+ "max_length": 142,
79
+ "min_length": 56,
80
+ "num_beams": 4
81
+ },
82
+ "summarization_xsum": {
83
+ "length_penalty": 1.0,
84
+ "max_length": 62,
85
+ "min_length": 11,
86
+ "num_beams": 6
87
+ }
88
+ },
89
+ "tokenizer_class": "IndoNLGTokenizer",
90
+ "torch_dtype": "float32",
91
+ "transformers_version": "4.33.1",
92
+ "use_cache": true,
93
+ "vocab_size": 40004
94
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
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_eos_token_id": 2,
8
+ "no_repeat_ngram_size": 3,
9
+ "num_beams": 4,
10
+ "pad_token_id": 1,
11
+ "transformers_version": "4.33.1"
12
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6cfd57b44d70dc15d2efe71451df27c22164110f2f38761030304d75ee92ea0
3
+ size 568959034