Hugging Face's logo

rubentito
/
longt5-tglobal-base-mpdocvqa

Text2Text Generation
Transformers
PyTorch
English
longt5
DocVQA
Document Question Answering
Document Visual Question Answering
Inference Endpoints
Model card Files Community
rubentito commited on
Commit
899da1a
•
1 Parent(s): f1f2a23

Upload 9 files

Browse files
Files changed (9) hide show
  1. added_tokens.json +5 -0
  2. config.json +35 -0
  3. experiment_config.yml +15 -0
  4. generation_config.json +7 -0
  5. pytorch_model.bin +3 -0
  6. special_tokens_map.json +113 -0
  7. spiece.model +3 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +112 -0
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<A>": 32102,
3
+ "<Q>": 32101,
4
+ "||": 32100
5
+ }
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tryolabs/long-t5-tglobal-base-blogpost-cqa",
3
+ "architectures": [
4
+ "LongT5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "encoder_attention_type": "transient-global",
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "global_block_size": 16,
16
+ "initializer_factor": 1.0,
17
+ "is_encoder_decoder": true,
18
+ "is_gated_act": true,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "local_radius": 127,
21
+ "model_type": "longt5",
22
+ "n_positions": 4096,
23
+ "num_decoder_layers": 12,
24
+ "num_heads": 12,
25
+ "num_layers": 12,
26
+ "output_past": true,
27
+ "pad_token_id": 0,
28
+ "relative_attention_max_distance": 128,
29
+ "relative_attention_num_buckets": 32,
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.27.2",
33
+ "use_cache": true,
34
+ "vocab_size": 32103
35
+ }
experiment_config.yml ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ batch_size: 8
2
+ data_parallel: false
3
+ dataset_name: MP-DocVQA
4
+ device: cuda
5
+ eval_start: true
6
+ images_dir: /data/users/rperez/MP-DocVQA/images/
7
+ imdb_dir: /data/users/rperez/imdb/collection
8
+ lr: 1e-4
9
+ model_name: LongT5
10
+ model_weights: tryolabs/long-t5-tglobal-base-blogpost-cqa
11
+ page_retrieval: Oracle
12
+ save_dir: save/
13
+ seed: 42
14
+ train_epochs: 10
15
+ warmup_iterations: 1000
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.27.2"
7
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:852f589c7ff25038f191fdd63fdbc28eb500c1fb912390787bc4bd4a0f955906
3
+ size 990296947
special_tokens_map.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_37>",
4
+ "<extra_id_97>",
5
+ "<extra_id_40>",
6
+ "<extra_id_69>",
7
+ "<extra_id_35>",
8
+ "<extra_id_50>",
9
+ "<extra_id_75>",
10
+ "<extra_id_59>",
11
+ "<extra_id_87>",
12
+ "<extra_id_43>",
13
+ "<extra_id_4>",
14
+ "<extra_id_54>",
15
+ "<extra_id_60>",
16
+ "<extra_id_48>",
17
+ "<extra_id_73>",
18
+ "<extra_id_34>",
19
+ "<extra_id_65>",
20
+ "<extra_id_78>",
21
+ "<extra_id_76>",
22
+ "<extra_id_1>",
23
+ "<extra_id_72>",
24
+ "<extra_id_64>",
25
+ "<extra_id_91>",
26
+ "<pad>",
27
+ "<extra_id_0>",
28
+ "<extra_id_80>",
29
+ "<extra_id_38>",
30
+ "<extra_id_15>",
31
+ "<extra_id_27>",
32
+ "<extra_id_70>",
33
+ "<extra_id_79>",
34
+ "<extra_id_94>",
35
+ "<extra_id_84>",
36
+ "<extra_id_25>",
37
+ "<extra_id_18>",
38
+ "<extra_id_13>",
39
+ "<extra_id_12>",
40
+ "<extra_id_61>",
41
+ "<extra_id_82>",
42
+ "<extra_id_6>",
43
+ "<extra_id_20>",
44
+ "<extra_id_16>",
45
+ "<extra_id_88>",
46
+ "<A>",
47
+ "<extra_id_66>",
48
+ "<extra_id_47>",
49
+ "<extra_id_31>",
50
+ "<extra_id_36>",
51
+ "<extra_id_62>",
52
+ "<extra_id_68>",
53
+ "<extra_id_83>",
54
+ "<extra_id_55>",
55
+ "<extra_id_23>",
56
+ "<extra_id_95>",
57
+ "<extra_id_19>",
58
+ "<extra_id_3>",
59
+ "<Q>",
60
+ "<extra_id_90>",
61
+ "<extra_id_57>",
62
+ "<extra_id_39>",
63
+ "<extra_id_5>",
64
+ "<extra_id_67>",
65
+ "<extra_id_24>",
66
+ "<extra_id_26>",
67
+ "<extra_id_53>",
68
+ "||",
69
+ "<extra_id_93>",
70
+ "<extra_id_98>",
71
+ "<extra_id_28>",
72
+ "<extra_id_32>",
73
+ "<extra_id_7>",
74
+ "<unk>",
75
+ "<extra_id_41>",
76
+ "<extra_id_2>",
77
+ "<extra_id_22>",
78
+ "<extra_id_77>",
79
+ "<extra_id_9>",
80
+ "<extra_id_99>",
81
+ "<extra_id_56>",
82
+ "<extra_id_44>",
83
+ "</s>",
84
+ "<extra_id_11>",
85
+ "<extra_id_74>",
86
+ "<extra_id_81>",
87
+ "<extra_id_29>",
88
+ "<extra_id_17>",
89
+ "<extra_id_30>",
90
+ "<extra_id_45>",
91
+ "<extra_id_96>",
92
+ "<extra_id_8>",
93
+ "<extra_id_58>",
94
+ "<extra_id_49>",
95
+ "<extra_id_46>",
96
+ "<extra_id_92>",
97
+ "<extra_id_14>",
98
+ "<extra_id_51>",
99
+ "<extra_id_71>",
100
+ "<extra_id_42>",
101
+ "<extra_id_10>",
102
+ "<extra_id_63>",
103
+ "<extra_id_85>",
104
+ "<extra_id_52>",
105
+ "<extra_id_89>",
106
+ "<extra_id_33>",
107
+ "<extra_id_21>",
108
+ "<extra_id_86>"
109
+ ],
110
+ "eos_token": "</s>",
111
+ "pad_token": "<pad>",
112
+ "unk_token": "<unk>"
113
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": "</s>",
105
+ "extra_ids": 100,
106
+ "low_cpu_mem_usage": true,
107
+ "model_max_length": 1000000000000000019884624838656,
108
+ "pad_token": "<pad>",
109
+ "special_tokens_map_file": null,
110
+ "tokenizer_class": "T5Tokenizer",
111
+ "unk_token": "<unk>"
112
+ }