Hugging Face's logo

farleyknight
/
patent-summarization-allen-led-large-2022-09-20

Text2Text Generation Transformers PyTorch
led generated_from_trainer Eval Results Inference Endpoints
Model card Files Community
2
farleyknight commited on
Commit
6c68269
•
1 Parent(s): 40b952c

Training in progress, step 500

Browse files
Files changed (9) hide show
  1. .gitignore +1 -0
  2. config.json +66 -0
  3. merges.txt +0 -0
  4. pytorch_model.bin +3 -0
  5. special_tokens_map.json +51 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +65 -0
  8. training_args.bin +3 -0
  9. vocab.json +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/led-large-16384-arxiv",
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": 12,
32
+ "decoder_start_token_id": 2,
33
+ "dropout": 0.1,
34
+ "encoder_attention_heads": 16,
35
+ "encoder_ffn_dim": 4096,
36
+ "encoder_layerdrop": 0.0,
37
+ "encoder_layers": 12,
38
+ "eos_token_id": 2,
39
+ "gradient_checkpointing": false,
40
+ "id2label": {
41
+ "0": "LABEL_0",
42
+ "1": "LABEL_1",
43
+ "2": "LABEL_2"
44
+ },
45
+ "init_std": 0.02,
46
+ "is_encoder_decoder": true,
47
+ "label2id": {
48
+ "LABEL_0": 0,
49
+ "LABEL_1": 1,
50
+ "LABEL_2": 2
51
+ },
52
+ "max_decoder_position_embeddings": 1024,
53
+ "max_encoder_position_embeddings": 16384,
54
+ "max_length": 512,
55
+ "max_position_embeddings": 1024,
56
+ "model_type": "led",
57
+ "num_beams": 4,
58
+ "num_hidden_layers": 12,
59
+ "output_past": false,
60
+ "pad_token_id": 1,
61
+ "prefix": " ",
62
+ "torch_dtype": "float32",
63
+ "transformers_version": "4.23.0.dev0",
64
+ "use_cache": true,
65
+ "vocab_size": 50265
66
+ }
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 sha256:5633a6ad142f430d85a683319cc4b70a90b86cc91f0c522eaa96ffc36a590706
3
+ size 1839604721
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
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": 16384,
37
+ "name_or_path": "allenai/led-large-16384-arxiv",
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": "/root/.cache/huggingface/hub/models--allenai--led-large-16384-arxiv/snapshots/6d566f57e58195c1810dd8497ccf7f015409a1a9/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 sha256:4429dfb73f66d16587363fe23d4d8253e3f83ac1e9a8695371cb645f755d731d
3
+ size 3695
vocab.json ADDED
The diff for this file is too large to render. See raw diff