Hayden Housen commited on
Commit
d12ea32
1 Parent(s): 3c419e7
config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/content/drive/MyDrive/TransformerExtSum Data/Abstractive/LED-Models/distil-led-large-16384/",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "gelu",
6
+ "architectures": [
7
+ "LEDForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "attention_window": [
11
+ 1024,
12
+ 1024,
13
+ 1024,
14
+ 1024,
15
+ 1024,
16
+ 1024,
17
+ 1024,
18
+ 1024,
19
+ 1024,
20
+ 1024,
21
+ 1024,
22
+ 1024
23
+ ],
24
+ "bos_token_id": 0,
25
+ "classif_dropout": 0.0,
26
+ "classifier_dropout": 0.0,
27
+ "d_model": 1024,
28
+ "decoder_attention_heads": 16,
29
+ "decoder_ffn_dim": 4096,
30
+ "decoder_layerdrop": 0.0,
31
+ "decoder_layers": 6,
32
+ "decoder_start_token_id": 2,
33
+ "dropout": 0.1,
34
+ "early_stopping": true,
35
+ "encoder_attention_heads": 16,
36
+ "encoder_ffn_dim": 4096,
37
+ "encoder_layerdrop": 0.0,
38
+ "encoder_layers": 12,
39
+ "eos_token_id": 2,
40
+ "force_bos_token_to_be_generated": true,
41
+ "gradient_checkpointing": false,
42
+ "id2label": {
43
+ "0": "LABEL_0",
44
+ "1": "LABEL_1",
45
+ "2": "LABEL_2"
46
+ },
47
+ "init_std": 0.02,
48
+ "is_encoder_decoder": true,
49
+ "label2id": {
50
+ "LABEL_0": 0,
51
+ "LABEL_1": 1,
52
+ "LABEL_2": 2
53
+ },
54
+ "length_penalty": 2.0,
55
+ "max_decoder_position_embeddings": 1024,
56
+ "max_encoder_position_embeddings": 16384,
57
+ "max_length": 142,
58
+ "min_length": 56,
59
+ "model_type": "led",
60
+ "no_repeat_ngram_size": 3,
61
+ "num_beams": 4,
62
+ "num_hidden_layers": 12,
63
+ "output_past": true,
64
+ "pad_token_id": 1,
65
+ "prefix": " ",
66
+ "replacing_rate": 0,
67
+ "student_decoder_layers": null,
68
+ "student_encoder_layers": null,
69
+ "task_specific_params": {
70
+ "summarization": {
71
+ "early_stopping": true,
72
+ "length_penalty": 2.0,
73
+ "max_length": 142,
74
+ "min_length": 56,
75
+ "no_repeat_ngram_size": 3,
76
+ "num_beams": 4
77
+ }
78
+ },
79
+ "transformers_version": "4.2.2",
80
+ "use_cache": true,
81
+ "vocab_size": 50264
82
+ }
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 sha256:2b469aa58f9c725e2e99564ae1b0787dfea700fb1a75ebee459eab87bf346121
3
+ size 1285068879
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