Hugging Face's logo

KellyShiiii
/
primer-crd3

Text2Text Generation
Transformers
PyTorch
led
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
1
KellyShiiii commited on
Commit
603318a
•
1 Parent(s): f2fec4a

Model save

Browse files
Files changed (10) hide show
  1. .gitignore +1 -0
  2. added_tokens.json +3 -0
  3. config.json +98 -0
  4. merges.txt +0 -0
  5. pytorch_model.bin +3 -0
  6. special_tokens_map.json +18 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +65 -0
  9. training_args.bin +3 -0
  10. vocab.json +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<doc-sep>": 50265
3
+ }
config.json ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/PRIMERA",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "gelu",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": false,
8
+ "architectures": [
9
+ "LEDForConditionalGeneration"
10
+ ],
11
+ "attention_dilation": [
12
+ 1,
13
+ 1,
14
+ 1,
15
+ 1,
16
+ 1,
17
+ 1,
18
+ 1,
19
+ 1,
20
+ 1,
21
+ 1,
22
+ 1,
23
+ 1
24
+ ],
25
+ "attention_dropout": 0.0,
26
+ "attention_mode": "sliding_chunks",
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
+ "classifier_dropout": 0.0,
45
+ "d_model": 1024,
46
+ "decoder_attention_heads": 16,
47
+ "decoder_ffn_dim": 4096,
48
+ "decoder_layerdrop": 0.0,
49
+ "decoder_layers": 12,
50
+ "decoder_start_token_id": 2,
51
+ "dropout": 0.1,
52
+ "encoder_attention_heads": 16,
53
+ "encoder_ffn_dim": 4096,
54
+ "encoder_layerdrop": 0.0,
55
+ "encoder_layers": 12,
56
+ "eos_token_id": 2,
57
+ "extra_pos_embeddings": 2,
58
+ "force_bos_token_to_be_generated": false,
59
+ "id2label": {
60
+ "0": "LABEL_0",
61
+ "1": "LABEL_1",
62
+ "2": "LABEL_2"
63
+ },
64
+ "init_std": 0.02,
65
+ "is_encoder_decoder": true,
66
+ "label2id": {
67
+ "LABEL_0": 0,
68
+ "LABEL_1": 1,
69
+ "LABEL_2": 2
70
+ },
71
+ "max_decoder_position_embeddings": 1024,
72
+ "max_encoder_position_embeddings": 4096,
73
+ "max_position_embeddings": 4096,
74
+ "model_type": "led",
75
+ "no_repeat_ngram_size": 3,
76
+ "normalize_before": false,
77
+ "normalize_embedding": true,
78
+ "num_hidden_layers": 12,
79
+ "output_past": false,
80
+ "pad_token_id": 1,
81
+ "prefix": " ",
82
+ "scale_embedding": false,
83
+ "static_position_embeddings": false,
84
+ "task_specific_params": {
85
+ "summarization": {
86
+ "early_stopping": true,
87
+ "length_penalty": 2.0,
88
+ "max_length": 142,
89
+ "min_length": 56,
90
+ "no_repeat_ngram_size": 3,
91
+ "num_beams": 4
92
+ }
93
+ },
94
+ "torch_dtype": "float32",
95
+ "transformers_version": "4.24.0",
96
+ "use_cache": true,
97
+ "vocab_size": 50266
98
+ }
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 sha256:03d47b2407b5c5ecd1c0f7c1cceaa5ed1c1b651a9ff00469abce8ef08b191310
3
+ size 1789290871
special_tokens_map.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<doc-sep>"
4
+ ],
5
+ "bos_token": "<s>",
6
+ "cls_token": "<s>",
7
+ "eos_token": "</s>",
8
+ "mask_token": {
9
+ "content": "<mask>",
10
+ "lstrip": true,
11
+ "normalized": false,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "pad_token": "<pad>",
16
+ "sep_token": "</s>",
17
+ "unk_token": "<unk>"
18
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "__type": "AddedToken",
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "errors": "replace",
28
+ "mask_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<mask>",
31
+ "lstrip": true,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "model_max_length": 4096,
37
+ "name_or_path": "allenai/PRIMERA",
38
+ "pad_token": {
39
+ "__type": "AddedToken",
40
+ "content": "<pad>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "sep_token": {
47
+ "__type": "AddedToken",
48
+ "content": "</s>",
49
+ "lstrip": false,
50
+ "normalized": true,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ },
54
+ "special_tokens_map_file": "/home/ubuntu/.cache/huggingface/hub/models--allenai--PRIMERA/snapshots/c9e8fee8c8ab2f19666d028ee7b0b552682b3785/special_tokens_map.json",
55
+ "tokenizer_class": "LEDTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": {
58
+ "__type": "AddedToken",
59
+ "content": "<unk>",
60
+ "lstrip": false,
61
+ "normalized": true,
62
+ "rstrip": false,
63
+ "single_word": false
64
+ }
65
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:672184a2da146b4c6bd8d7794e78cf3139d7e50a73c1c728faea905f7a41acf9
3
+ size 3503
vocab.json ADDED
The diff for this file is too large to render. See raw diff