patrickvonplaten commited on
Commit
bd58652
1 Parent(s): 877e7ce
config.json ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_num_labels": 3,
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForConditionalGeneration"
9
+ ],
10
+ "attention_dilation": [
11
+ 1,
12
+ 1,
13
+ 1,
14
+ 1,
15
+ 1,
16
+ 1,
17
+ 1,
18
+ 1,
19
+ 1,
20
+ 1,
21
+ 1,
22
+ 1
23
+ ],
24
+ "attention_dropout": 0.0,
25
+ "attention_mode": "sliding_chunks",
26
+ "attention_probs_dropout_prob": 0.0,
27
+ "attention_window": [
28
+ 512,
29
+ 512,
30
+ 512,
31
+ 512,
32
+ 512,
33
+ 512,
34
+ 512,
35
+ 512,
36
+ 512,
37
+ 512,
38
+ 512,
39
+ 512
40
+ ],
41
+ "autoregressive": false,
42
+ "bos_token_id": 0,
43
+ "classif_dropout": 0.0,
44
+ "d_model": 1024,
45
+ "decoder_attention_heads": 16,
46
+ "decoder_ffn_dim": 4096,
47
+ "decoder_layerdrop": 0.0,
48
+ "decoder_layers": 12,
49
+ "decoder_start_token_id": 2,
50
+ "dropout": 0.1,
51
+ "encoder_attention_heads": 16,
52
+ "encoder_ffn_dim": 4096,
53
+ "encoder_layerdrop": 0.0,
54
+ "encoder_layers": 12,
55
+ "eos_token_id": 2,
56
+ "extra_pos_embeddings": 2,
57
+ "gradient_checkpointing": false,
58
+ "id2label": {
59
+ "0": "LABEL_0",
60
+ "1": "LABEL_1",
61
+ "2": "LABEL_2"
62
+ },
63
+ "init_std": 0.02,
64
+ "is_encoder_decoder": true,
65
+ "label2id": {
66
+ "LABEL_0": 0,
67
+ "LABEL_1": 1,
68
+ "LABEL_2": 2
69
+ },
70
+ "max_decoder_position_embeddings": 1024,
71
+ "max_encoder_position_embeddings": 16384,
72
+ "model_type": "bart",
73
+ "normalize_before": false,
74
+ "normalize_embedding": true,
75
+ "num_hidden_layers": 12,
76
+ "output_past": false,
77
+ "pad_token_id": 1,
78
+ "prefix": " ",
79
+ "scale_embedding": false,
80
+ "static_position_embeddings": false,
81
+ "task_specific_params": {
82
+ "summarization": {
83
+ "early_stopping": true,
84
+ "length_penalty": 2.0,
85
+ "max_length": 142,
86
+ "min_length": 56,
87
+ "no_repeat_ngram_size": 3,
88
+ "num_beams": 4
89
+ }
90
+ },
91
+ "vocab_size": 50265
92
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d68af582e11d949b625d046bc6a7a7c7e44d1af14a6a2024efad7e485b7480e9
3
+ size 1688408119
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model_max_length": 16384}
vocab.json ADDED
The diff for this file is too large to render. See raw diff