DylanJHJ commited on
Commit
dbabcce
1 Parent(s): ad87ded

upload vlt5 epoch30 from repo s gdrive

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "VLT5_epoch30",
3
+ "activation_dropout": 0.1,
4
+ "architectures": [
5
+ "T5ForConditionalGeneration"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "classifier": false,
9
+ "classifier_dropout": 0.0,
10
+ "d_ff": 3072,
11
+ "d_kv": 64,
12
+ "d_model": 768,
13
+ "decoder_start_token_id": 0,
14
+ "dense_act_fn": "relu",
15
+ "dropout": 0.1,
16
+ "dropout_rate": 0.1,
17
+ "eos_token_id": 1,
18
+ "feat_dim": 2048,
19
+ "feed_forward_proj": "relu",
20
+ "individual_vis_layer_norm": true,
21
+ "initializer_factor": 1.0,
22
+ "is_encoder_decoder": true,
23
+ "is_gated_act": false,
24
+ "layer_norm_epsilon": 1e-06,
25
+ "losses": "lm,obj,attr,feat",
26
+ "model_type": "t5",
27
+ "n_images": 2,
28
+ "n_positions": 512,
29
+ "num_decoder_layers": 12,
30
+ "num_heads": 12,
31
+ "num_layers": 12,
32
+ "output_past": true,
33
+ "pad_token_id": 0,
34
+ "pos_dim": 4,
35
+ "relative_attention_max_distance": 128,
36
+ "relative_attention_num_buckets": 32,
37
+ "share_vis_lang_layer_norm": true,
38
+ "task_specific_params": {
39
+ "summarization": {
40
+ "early_stopping": true,
41
+ "length_penalty": 2.0,
42
+ "max_length": 200,
43
+ "min_length": 30,
44
+ "no_repeat_ngram_size": 3,
45
+ "num_beams": 4,
46
+ "prefix": "summarize: "
47
+ },
48
+ "translation_en_to_de": {
49
+ "early_stopping": true,
50
+ "max_length": 300,
51
+ "num_beams": 4,
52
+ "prefix": "translate English to German: "
53
+ },
54
+ "translation_en_to_fr": {
55
+ "early_stopping": true,
56
+ "max_length": 300,
57
+ "num_beams": 4,
58
+ "prefix": "translate English to French: "
59
+ },
60
+ "translation_en_to_ro": {
61
+ "early_stopping": true,
62
+ "max_length": 300,
63
+ "num_beams": 4,
64
+ "prefix": "translate English to Romanian: "
65
+ }
66
+ },
67
+ "transformers_version": "4.33.1",
68
+ "use_cache": true,
69
+ "use_vis_layer_norm": true,
70
+ "use_vis_order_embedding": true,
71
+ "vocab_size": 32200
72
+ }
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": "4.33.1"
7
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7093124a2bf5f101be912ea12fceb9fd39cb50ea914cdd75f6853798cbe2011
3
+ size 898290327
special_tokens_map.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "<vis_extra_id_0>",
104
+ "<vis_extra_id_1>",
105
+ "<vis_extra_id_2>",
106
+ "<vis_extra_id_3>",
107
+ "<vis_extra_id_4>",
108
+ "<vis_extra_id_5>",
109
+ "<vis_extra_id_6>",
110
+ "<vis_extra_id_7>",
111
+ "<vis_extra_id_8>",
112
+ "<vis_extra_id_9>",
113
+ "<vis_extra_id_10>",
114
+ "<vis_extra_id_11>",
115
+ "<vis_extra_id_12>",
116
+ "<vis_extra_id_13>",
117
+ "<vis_extra_id_14>",
118
+ "<vis_extra_id_15>",
119
+ "<vis_extra_id_16>",
120
+ "<vis_extra_id_17>",
121
+ "<vis_extra_id_18>",
122
+ "<vis_extra_id_19>",
123
+ "<vis_extra_id_20>",
124
+ "<vis_extra_id_21>",
125
+ "<vis_extra_id_22>",
126
+ "<vis_extra_id_23>",
127
+ "<vis_extra_id_24>",
128
+ "<vis_extra_id_25>",
129
+ "<vis_extra_id_26>",
130
+ "<vis_extra_id_27>",
131
+ "<vis_extra_id_28>",
132
+ "<vis_extra_id_29>",
133
+ "<vis_extra_id_30>",
134
+ "<vis_extra_id_31>",
135
+ "<vis_extra_id_32>",
136
+ "<vis_extra_id_33>",
137
+ "<vis_extra_id_34>",
138
+ "<vis_extra_id_35>",
139
+ "<vis_extra_id_36>",
140
+ "<vis_extra_id_37>",
141
+ "<vis_extra_id_38>",
142
+ "<vis_extra_id_39>",
143
+ "<vis_extra_id_40>",
144
+ "<vis_extra_id_41>",
145
+ "<vis_extra_id_42>",
146
+ "<vis_extra_id_43>",
147
+ "<vis_extra_id_44>",
148
+ "<vis_extra_id_45>",
149
+ "<vis_extra_id_46>",
150
+ "<vis_extra_id_47>",
151
+ "<vis_extra_id_48>",
152
+ "<vis_extra_id_49>",
153
+ "<vis_extra_id_50>",
154
+ "<vis_extra_id_51>",
155
+ "<vis_extra_id_52>",
156
+ "<vis_extra_id_53>",
157
+ "<vis_extra_id_54>",
158
+ "<vis_extra_id_55>",
159
+ "<vis_extra_id_56>",
160
+ "<vis_extra_id_57>",
161
+ "<vis_extra_id_58>",
162
+ "<vis_extra_id_59>",
163
+ "<vis_extra_id_60>",
164
+ "<vis_extra_id_61>",
165
+ "<vis_extra_id_62>",
166
+ "<vis_extra_id_63>",
167
+ "<vis_extra_id_64>",
168
+ "<vis_extra_id_65>",
169
+ "<vis_extra_id_66>",
170
+ "<vis_extra_id_67>",
171
+ "<vis_extra_id_68>",
172
+ "<vis_extra_id_69>",
173
+ "<vis_extra_id_70>",
174
+ "<vis_extra_id_71>",
175
+ "<vis_extra_id_72>",
176
+ "<vis_extra_id_73>",
177
+ "<vis_extra_id_74>",
178
+ "<vis_extra_id_75>",
179
+ "<vis_extra_id_76>",
180
+ "<vis_extra_id_77>",
181
+ "<vis_extra_id_78>",
182
+ "<vis_extra_id_79>",
183
+ "<vis_extra_id_80>",
184
+ "<vis_extra_id_81>",
185
+ "<vis_extra_id_82>",
186
+ "<vis_extra_id_83>",
187
+ "<vis_extra_id_84>",
188
+ "<vis_extra_id_85>",
189
+ "<vis_extra_id_86>",
190
+ "<vis_extra_id_87>",
191
+ "<vis_extra_id_88>",
192
+ "<vis_extra_id_89>",
193
+ "<vis_extra_id_90>",
194
+ "<vis_extra_id_91>",
195
+ "<vis_extra_id_92>",
196
+ "<vis_extra_id_93>",
197
+ "<vis_extra_id_94>",
198
+ "<vis_extra_id_95>",
199
+ "<vis_extra_id_96>",
200
+ "<vis_extra_id_97>",
201
+ "<vis_extra_id_98>",
202
+ "<vis_extra_id_99>"
203
+ ],
204
+ "eos_token": "</s>",
205
+ "pad_token": "<pad>",
206
+ "unk_token": "<unk>"
207
+ }
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 +1,213 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "<vis_extra_id_0>",
104
+ "<vis_extra_id_1>",
105
+ "<vis_extra_id_2>",
106
+ "<vis_extra_id_3>",
107
+ "<vis_extra_id_4>",
108
+ "<vis_extra_id_5>",
109
+ "<vis_extra_id_6>",
110
+ "<vis_extra_id_7>",
111
+ "<vis_extra_id_8>",
112
+ "<vis_extra_id_9>",
113
+ "<vis_extra_id_10>",
114
+ "<vis_extra_id_11>",
115
+ "<vis_extra_id_12>",
116
+ "<vis_extra_id_13>",
117
+ "<vis_extra_id_14>",
118
+ "<vis_extra_id_15>",
119
+ "<vis_extra_id_16>",
120
+ "<vis_extra_id_17>",
121
+ "<vis_extra_id_18>",
122
+ "<vis_extra_id_19>",
123
+ "<vis_extra_id_20>",
124
+ "<vis_extra_id_21>",
125
+ "<vis_extra_id_22>",
126
+ "<vis_extra_id_23>",
127
+ "<vis_extra_id_24>",
128
+ "<vis_extra_id_25>",
129
+ "<vis_extra_id_26>",
130
+ "<vis_extra_id_27>",
131
+ "<vis_extra_id_28>",
132
+ "<vis_extra_id_29>",
133
+ "<vis_extra_id_30>",
134
+ "<vis_extra_id_31>",
135
+ "<vis_extra_id_32>",
136
+ "<vis_extra_id_33>",
137
+ "<vis_extra_id_34>",
138
+ "<vis_extra_id_35>",
139
+ "<vis_extra_id_36>",
140
+ "<vis_extra_id_37>",
141
+ "<vis_extra_id_38>",
142
+ "<vis_extra_id_39>",
143
+ "<vis_extra_id_40>",
144
+ "<vis_extra_id_41>",
145
+ "<vis_extra_id_42>",
146
+ "<vis_extra_id_43>",
147
+ "<vis_extra_id_44>",
148
+ "<vis_extra_id_45>",
149
+ "<vis_extra_id_46>",
150
+ "<vis_extra_id_47>",
151
+ "<vis_extra_id_48>",
152
+ "<vis_extra_id_49>",
153
+ "<vis_extra_id_50>",
154
+ "<vis_extra_id_51>",
155
+ "<vis_extra_id_52>",
156
+ "<vis_extra_id_53>",
157
+ "<vis_extra_id_54>",
158
+ "<vis_extra_id_55>",
159
+ "<vis_extra_id_56>",
160
+ "<vis_extra_id_57>",
161
+ "<vis_extra_id_58>",
162
+ "<vis_extra_id_59>",
163
+ "<vis_extra_id_60>",
164
+ "<vis_extra_id_61>",
165
+ "<vis_extra_id_62>",
166
+ "<vis_extra_id_63>",
167
+ "<vis_extra_id_64>",
168
+ "<vis_extra_id_65>",
169
+ "<vis_extra_id_66>",
170
+ "<vis_extra_id_67>",
171
+ "<vis_extra_id_68>",
172
+ "<vis_extra_id_69>",
173
+ "<vis_extra_id_70>",
174
+ "<vis_extra_id_71>",
175
+ "<vis_extra_id_72>",
176
+ "<vis_extra_id_73>",
177
+ "<vis_extra_id_74>",
178
+ "<vis_extra_id_75>",
179
+ "<vis_extra_id_76>",
180
+ "<vis_extra_id_77>",
181
+ "<vis_extra_id_78>",
182
+ "<vis_extra_id_79>",
183
+ "<vis_extra_id_80>",
184
+ "<vis_extra_id_81>",
185
+ "<vis_extra_id_82>",
186
+ "<vis_extra_id_83>",
187
+ "<vis_extra_id_84>",
188
+ "<vis_extra_id_85>",
189
+ "<vis_extra_id_86>",
190
+ "<vis_extra_id_87>",
191
+ "<vis_extra_id_88>",
192
+ "<vis_extra_id_89>",
193
+ "<vis_extra_id_90>",
194
+ "<vis_extra_id_91>",
195
+ "<vis_extra_id_92>",
196
+ "<vis_extra_id_93>",
197
+ "<vis_extra_id_94>",
198
+ "<vis_extra_id_95>",
199
+ "<vis_extra_id_96>",
200
+ "<vis_extra_id_97>",
201
+ "<vis_extra_id_98>",
202
+ "<vis_extra_id_99>"
203
+ ],
204
+ "clean_up_tokenization_spaces": true,
205
+ "do_lower_case": true,
206
+ "eos_token": "</s>",
207
+ "extra_ids": 100,
208
+ "model_max_length": 512,
209
+ "pad_token": "<pad>",
210
+ "tokenizer_class": "VLT5Tokenizer",
211
+ "unk_token": "<unk>",
212
+ "vis_extra_ids": 100
213
+ }