Hugging Face's logo

google
/
pix2struct-infographics-vqa-large

Visual Question Answering Transformers PyTorch 5 languages pix2struct text2text-generation
Model card Files Community
ybelkada HF staff commited on
Commit
834f955
•
1 Parent(s): 749b347

Upload Pix2StructForConditionalGeneration

Browse files
Files changed (2) hide show
  1. config.json +177 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,177 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "/home/younes_huggingface_co/code/pix2struct-checkpoints/pix2struct-infographics-vqa-large",
4
+ "architectures": [
5
+ "Pix2StructForConditionalGeneration"
6
+ ],
7
+ "decoder_start_token_id": 0,
8
+ "initializer_factor": 1.0,
9
+ "initializer_range": 0.02,
10
+ "is_vqa": false,
11
+ "model_type": "pix2struct",
12
+ "pad_token_id": 0,
13
+ "text_config": {
14
+ "_name_or_path": "",
15
+ "add_cross_attention": false,
16
+ "architectures": null,
17
+ "bad_words_ids": null,
18
+ "begin_suppress_tokens": null,
19
+ "bos_token_id": null,
20
+ "chunk_size_feed_forward": 0,
21
+ "cross_attention_hidden_size": null,
22
+ "d_ff": 3968,
23
+ "d_kv": 64,
24
+ "decoder_start_token_id": 0,
25
+ "dense_act_fn": "gelu_new",
26
+ "diversity_penalty": 0.0,
27
+ "do_sample": false,
28
+ "dropout_rate": 0.1,
29
+ "early_stopping": false,
30
+ "encoder_hidden_size": 1536,
31
+ "encoder_no_repeat_ngram_size": 0,
32
+ "eos_token_id": 1,
33
+ "exponential_decay_length_penalty": null,
34
+ "finetuning_task": null,
35
+ "forced_bos_token_id": null,
36
+ "forced_eos_token_id": null,
37
+ "hidden_size": 1536,
38
+ "id2label": {
39
+ "0": "LABEL_0",
40
+ "1": "LABEL_1"
41
+ },
42
+ "initializer_factor": 1.0,
43
+ "initializer_range": 0.02,
44
+ "is_decoder": false,
45
+ "is_encoder_decoder": false,
46
+ "label2id": {
47
+ "LABEL_0": 0,
48
+ "LABEL_1": 1
49
+ },
50
+ "layer_norm_epsilon": 1e-06,
51
+ "length_penalty": 1.0,
52
+ "max_length": 20,
53
+ "min_length": 0,
54
+ "model_type": "pix2struct_text_model",
55
+ "no_repeat_ngram_size": 0,
56
+ "num_beam_groups": 1,
57
+ "num_beams": 1,
58
+ "num_heads": 24,
59
+ "num_layers": 18,
60
+ "num_return_sequences": 1,
61
+ "output_attentions": false,
62
+ "output_hidden_states": false,
63
+ "output_scores": false,
64
+ "pad_token_id": 0,
65
+ "prefix": null,
66
+ "problem_type": null,
67
+ "pruned_heads": {},
68
+ "relative_attention_max_distance": 128,
69
+ "relative_attention_num_buckets": 32,
70
+ "remove_invalid_values": false,
71
+ "repetition_penalty": 1.0,
72
+ "return_dict": true,
73
+ "return_dict_in_generate": false,
74
+ "sep_token_id": null,
75
+ "suppress_tokens": null,
76
+ "task_specific_params": null,
77
+ "temperature": 1.0,
78
+ "tf_legacy_loss": false,
79
+ "tie_encoder_decoder": false,
80
+ "tie_word_embeddings": true,
81
+ "tokenizer_class": null,
82
+ "top_k": 50,
83
+ "top_p": 1.0,
84
+ "torch_dtype": null,
85
+ "torchscript": false,
86
+ "transformers_version": "4.28.0.dev0",
87
+ "typical_p": 1.0,
88
+ "use_bfloat16": false,
89
+ "use_cache": false,
90
+ "vocab_size": 50244
91
+ },
92
+ "torch_dtype": "float32",
93
+ "transformers_version": null,
94
+ "vision_config": {
95
+ "_name_or_path": "",
96
+ "add_cross_attention": false,
97
+ "architectures": null,
98
+ "attention_dropout": 0.0,
99
+ "bad_words_ids": null,
100
+ "begin_suppress_tokens": null,
101
+ "bos_token_id": null,
102
+ "chunk_size_feed_forward": 0,
103
+ "cross_attention_hidden_size": null,
104
+ "d_ff": 3968,
105
+ "d_kv": 64,
106
+ "decoder_start_token_id": null,
107
+ "dense_act_fn": "gelu_new",
108
+ "diversity_penalty": 0.0,
109
+ "do_sample": false,
110
+ "dropout_rate": 0.0,
111
+ "early_stopping": false,
112
+ "encoder_no_repeat_ngram_size": 0,
113
+ "eos_token_id": null,
114
+ "exponential_decay_length_penalty": null,
115
+ "finetuning_task": null,
116
+ "forced_bos_token_id": null,
117
+ "forced_eos_token_id": null,
118
+ "hidden_size": 1536,
119
+ "id2label": {
120
+ "0": "LABEL_0",
121
+ "1": "LABEL_1"
122
+ },
123
+ "initializer_factor": 1.0,
124
+ "initializer_range": 0.02,
125
+ "is_decoder": false,
126
+ "is_encoder_decoder": false,
127
+ "label2id": {
128
+ "LABEL_0": 0,
129
+ "LABEL_1": 1
130
+ },
131
+ "layer_norm_bias": false,
132
+ "layer_norm_eps": 1e-06,
133
+ "length_penalty": 1.0,
134
+ "max_length": 20,
135
+ "min_length": 0,
136
+ "model_type": "pix2struct_vision_model",
137
+ "no_repeat_ngram_size": 0,
138
+ "num_attention_heads": 24,
139
+ "num_beam_groups": 1,
140
+ "num_beams": 1,
141
+ "num_channels": 3,
142
+ "num_hidden_layers": 18,
143
+ "num_return_sequences": 1,
144
+ "output_attentions": false,
145
+ "output_hidden_states": false,
146
+ "output_scores": false,
147
+ "pad_token_id": null,
148
+ "patch_embed_hidden_size": 768,
149
+ "patch_size": 16,
150
+ "prefix": null,
151
+ "problem_type": null,
152
+ "projection_dim": 768,
153
+ "pruned_heads": {},
154
+ "relative_attention_max_distance": 128,
155
+ "relative_attention_num_buckets": 32,
156
+ "remove_invalid_values": false,
157
+ "repetition_penalty": 1.0,
158
+ "return_dict": true,
159
+ "return_dict_in_generate": false,
160
+ "sep_token_id": null,
161
+ "seq_len": 4096,
162
+ "suppress_tokens": null,
163
+ "task_specific_params": null,
164
+ "temperature": 1.0,
165
+ "tf_legacy_loss": false,
166
+ "tie_encoder_decoder": false,
167
+ "tie_word_embeddings": true,
168
+ "tokenizer_class": null,
169
+ "top_k": 50,
170
+ "top_p": 1.0,
171
+ "torch_dtype": null,
172
+ "torchscript": false,
173
+ "transformers_version": "4.28.0.dev0",
174
+ "typical_p": 1.0,
175
+ "use_bfloat16": false
176
+ }
177
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:389f6faac8d1ef7971ef1fdb690c5d82d6fb606cb22861f37e8fa7bf8875f9d9
3
+ size 5344571621