Hugging Face's logo

zphilip48
/
nougat-middle-cn

Transformers
PyTorch
nougat
Inference Endpoints
Model card Files Community
1
zphilip48 commited on
Commit
d1ba1a3
·
verified ·
1 Parent(s): b6920dc

Upload 6 files

Browse files

the first submission

Files changed (6) hide show
  1. config.json +32 -0
  2. config.yaml +52 -0
  3. pytorch_model.bin +3 -0
  4. special_tokens_map.json +6 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +202 -0
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "align_long_axis": false,
3
+ "architectures": [
4
+ "NougatModel"
5
+ ],
6
+ "decoder_layer": 6,
7
+ "embed_dim": 128,
8
+ "encoder_layer": [
9
+ 2,
10
+ 2,
11
+ 14,
12
+ 2
13
+ ],
14
+ "hidden_dimension": 1024,
15
+ "input_size": [
16
+ 896,
17
+ 672
18
+ ],
19
+ "max_length": 4096,
20
+ "max_position_embeddings": 4096,
21
+ "model_type": "nougat",
22
+ "num_heads": [
23
+ 4,
24
+ 8,
25
+ 16,
26
+ 32
27
+ ],
28
+ "patch_size": 4,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.34.1",
31
+ "window_size": 7
32
+ }
config.yaml ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ resume_from_checkpoint_path: None
2
+ result_path: 'result'
3
+ model_path: None
4
+ dataset_paths:
5
+ - '/root/autodl-tmp/Nougat-Data/train.jsonl'
6
+ tokenizer: './config/tokenizer.json'
7
+ exp_name: 'nougat-middle'
8
+ train_batch_sizes:
9
+ - 1
10
+ num_workers: 4
11
+ val_batch_sizes:
12
+ - 1
13
+ val_batches: 1
14
+ input_size:
15
+ - 896
16
+ - 672
17
+ max_length: 4096
18
+ max_position_embeddings: 4096
19
+ accumulate_grad_batches: 3
20
+ window_size: 7
21
+ patch_size: 4
22
+ embed_dim: 128
23
+ hidden_dimension: 1024
24
+ num_heads:
25
+ - 4
26
+ - 8
27
+ - 16
28
+ - 32
29
+ encoder_layer:
30
+ - 2
31
+ - 2
32
+ - 14
33
+ - 2
34
+ decoder_layer: 6
35
+ align_long_axis: False
36
+ num_nodes: 1
37
+ seed: 25
38
+ lr: 5e-05
39
+ min_lr: 7.5e-06
40
+ lr_step: 16
41
+ gamma: 0.9996
42
+ warmup_steps: 250
43
+ num_training_samples_per_epoch: 10000
44
+ max_epochs: 30
45
+ max_steps: -1
46
+ val_check_interval: None
47
+ check_val_every_n_epoch: 1
48
+ gradient_clip_val: 0.5
49
+ verbose: False
50
+ debug: False
51
+ job: None
52
+ exp_version: '20240206_132202'
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94d5d26420db2b4b1bb6690ee35bc181c87a3a35cc078f897c76b9108a7af009
3
+ size 934321433
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[START_REF]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "[END_REF]",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "[IMAGE]",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "<fragments>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "8": {
68
+ "content": "</fragments>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "9": {
76
+ "content": "<work>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "10": {
84
+ "content": "</work>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "11": {
92
+ "content": "[START_SUP]",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "12": {
100
+ "content": "[END_SUP]",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "13": {
108
+ "content": "[START_SUB]",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "14": {
116
+ "content": "[END_SUB]",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "15": {
124
+ "content": "[START_DNA]",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "16": {
132
+ "content": "[END_DNA]",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "17": {
140
+ "content": "[START_AMINO]",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "18": {
148
+ "content": "[END_AMINO]",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "19": {
156
+ "content": "[START_SMILES]",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "20": {
164
+ "content": "[END_SMILES]",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "21": {
172
+ "content": "[START_I_SMILES]",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "22": {
180
+ "content": "[END_I_SMILES]",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ }
187
+ },
188
+ "bos_token": "<s>",
189
+ "clean_up_tokenization_spaces": true,
190
+ "eos_token": "</s>",
191
+ "max_length": 4096,
192
+ "model_max_length": 1000000000000000019884624838656,
193
+ "pad_to_multiple_of": null,
194
+ "pad_token": "<pad>",
195
+ "pad_token_type_id": 0,
196
+ "padding_side": "right",
197
+ "stride": 0,
198
+ "tokenizer_class": "PreTrainedTokenizerFast",
199
+ "truncation_side": "right",
200
+ "truncation_strategy": "longest_first",
201
+ "unk_token": "<unk>"
202
+ }