ybelkada commited on
Commit
e523468
1 Parent(s): 773079a

Upload Pix2StructForConditionalGeneration

Browse files
Files changed (2) hide show
  1. config.json +180 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,180 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "/home/younes_huggingface_co/code/pix2struct-checkpoints/pix2struct-widget-captioning-large",
4
+ "architectures": [
5
+ "Pix2StructForConditionalGeneration"
6
+ ],
7
+ "decoder_start_token_id": 0,
8
+ "initializer_factor": 1.0,
9
+ "initializer_range": 0.02,
10
+ "model_type": "pix2struct",
11
+ "pad_token_id": 0,
12
+ "text_config": {
13
+ "_name_or_path": "",
14
+ "add_cross_attention": false,
15
+ "architectures": null,
16
+ "bad_words_ids": null,
17
+ "begin_suppress_tokens": null,
18
+ "bos_token_id": null,
19
+ "chunk_size_feed_forward": 0,
20
+ "cross_attention_hidden_size": null,
21
+ "d_ff": 3968,
22
+ "d_kv": 64,
23
+ "decoder_start_token_id": 0,
24
+ "dense_act_fn": "gelu_new",
25
+ "diversity_penalty": 0.0,
26
+ "do_sample": false,
27
+ "dropout_rate": 0.1,
28
+ "early_stopping": false,
29
+ "encoder_hidden_size": 1536,
30
+ "encoder_no_repeat_ngram_size": 0,
31
+ "eos_token_id": 1,
32
+ "exponential_decay_length_penalty": null,
33
+ "finetuning_task": null,
34
+ "forced_bos_token_id": null,
35
+ "forced_eos_token_id": null,
36
+ "hidden_size": 1536,
37
+ "id2label": {
38
+ "0": "LABEL_0",
39
+ "1": "LABEL_1"
40
+ },
41
+ "initializer_factor": 1.0,
42
+ "initializer_range": 0.02,
43
+ "is_decoder": false,
44
+ "is_encoder_decoder": false,
45
+ "label2id": {
46
+ "LABEL_0": 0,
47
+ "LABEL_1": 1
48
+ },
49
+ "layer_norm_epsilon": 1e-06,
50
+ "length_penalty": 1.0,
51
+ "max_length": 20,
52
+ "min_length": 0,
53
+ "model_type": "pix2struct_text_model",
54
+ "no_repeat_ngram_size": 0,
55
+ "num_beam_groups": 1,
56
+ "num_beams": 1,
57
+ "num_heads": 24,
58
+ "num_layers": 18,
59
+ "num_return_sequences": 1,
60
+ "output_attentions": false,
61
+ "output_hidden_states": false,
62
+ "output_scores": false,
63
+ "pad_token_id": 0,
64
+ "prefix": null,
65
+ "problem_type": null,
66
+ "pruned_heads": {},
67
+ "relative_attention_max_distance": 128,
68
+ "relative_attention_num_buckets": 32,
69
+ "remove_invalid_values": false,
70
+ "repetition_penalty": 1.0,
71
+ "return_dict": true,
72
+ "return_dict_in_generate": false,
73
+ "sep_token_id": null,
74
+ "suppress_tokens": null,
75
+ "task_specific_params": null,
76
+ "temperature": 1.0,
77
+ "tf_legacy_loss": false,
78
+ "tie_encoder_decoder": false,
79
+ "tie_word_embeddings": true,
80
+ "tokenizer_class": null,
81
+ "top_k": 50,
82
+ "top_p": 1.0,
83
+ "torch_dtype": null,
84
+ "torchscript": false,
85
+ "transformers_version": "4.27.0.dev0",
86
+ "typical_p": 1.0,
87
+ "use_bfloat16": false,
88
+ "use_cache": false,
89
+ "vocab_size": 50244
90
+ },
91
+ "torch_dtype": "float32",
92
+ "transformers_version": null,
93
+ "vision_config": {
94
+ "_name_or_path": "",
95
+ "add_cross_attention": false,
96
+ "architectures": null,
97
+ "attention_dropout": 0.0,
98
+ "bad_words_ids": null,
99
+ "begin_suppress_tokens": null,
100
+ "bos_token_id": null,
101
+ "chunk_size_feed_forward": 0,
102
+ "cross_attention_hidden_size": null,
103
+ "d_ff": 3968,
104
+ "d_kv": 64,
105
+ "decoder_start_token_id": null,
106
+ "dense_act_fn": "gelu_new",
107
+ "diversity_penalty": 0.0,
108
+ "do_sample": false,
109
+ "dropout_rate": 0.0,
110
+ "early_stopping": false,
111
+ "encoder_no_repeat_ngram_size": 0,
112
+ "eos_token_id": null,
113
+ "exponential_decay_length_penalty": null,
114
+ "finetuning_task": null,
115
+ "forced_bos_token_id": null,
116
+ "forced_eos_token_id": null,
117
+ "hidden_dropout_prob": 0.0,
118
+ "hidden_size": 1536,
119
+ "id2label": {
120
+ "0": "LABEL_0",
121
+ "1": "LABEL_1"
122
+ },
123
+ "image_size": 384,
124
+ "initializer_factor": 1.0,
125
+ "initializer_range": 0.02,
126
+ "is_decoder": false,
127
+ "is_encoder_decoder": false,
128
+ "label2id": {
129
+ "LABEL_0": 0,
130
+ "LABEL_1": 1
131
+ },
132
+ "layer_norm_bias": false,
133
+ "layer_norm_eps": 1e-06,
134
+ "length_penalty": 1.0,
135
+ "max_length": 20,
136
+ "min_length": 0,
137
+ "mlp_bias": false,
138
+ "model_type": "pix2struct_vision_model",
139
+ "no_repeat_ngram_size": 0,
140
+ "num_attention_heads": 24,
141
+ "num_beam_groups": 1,
142
+ "num_beams": 1,
143
+ "num_channels": 3,
144
+ "num_hidden_layers": 18,
145
+ "num_return_sequences": 1,
146
+ "output_attentions": false,
147
+ "output_hidden_states": false,
148
+ "output_scores": false,
149
+ "pad_token_id": null,
150
+ "patch_embed_hidden_size": 768,
151
+ "patch_size": 16,
152
+ "prefix": null,
153
+ "problem_type": null,
154
+ "projection_dim": 768,
155
+ "pruned_heads": {},
156
+ "qkv_bias": false,
157
+ "relative_attention_max_distance": 128,
158
+ "relative_attention_num_buckets": 32,
159
+ "remove_invalid_values": false,
160
+ "repetition_penalty": 1.0,
161
+ "return_dict": true,
162
+ "return_dict_in_generate": false,
163
+ "sep_token_id": null,
164
+ "seq_len": 4096,
165
+ "suppress_tokens": null,
166
+ "task_specific_params": null,
167
+ "temperature": 1.0,
168
+ "tf_legacy_loss": false,
169
+ "tie_encoder_decoder": false,
170
+ "tie_word_embeddings": true,
171
+ "tokenizer_class": null,
172
+ "top_k": 50,
173
+ "top_p": 1.0,
174
+ "torch_dtype": null,
175
+ "torchscript": false,
176
+ "transformers_version": "4.27.0.dev0",
177
+ "typical_p": 1.0,
178
+ "use_bfloat16": false
179
+ }
180
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:613c85a4f2b8d3ffcf26fa5365ddcb50ce3e30b3ddea97d9a48c69d309b8efc0
3
+ size 5344571621