Hugging Face's logo

mPLUG
/
DocOwl1.5-stage1

Transformers
PyTorch
Safetensors
English
mplug_docowl
OCR-free Document Understanding
Struct-aware Parsing
Text Grounding
Inference Endpoints
Model card Files Community
1
AnwenHu commited on
Commit
4489082
•
1 Parent(s): 7d1aed8

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +170 -0
config.json ADDED
@@ -0,0 +1,170 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attention_bias": false,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "hidden_act": "silu",
6
+ "hidden_size": 4096,
7
+ "initializer_range": 0.02,
8
+ "intermediate_size": 11008,
9
+ "max_position_embeddings": 2048,
10
+ "model_type": "mplug_docowl",
11
+ "num_attention_heads": 32,
12
+ "num_hidden_layers": 32,
13
+ "num_key_value_heads": 32,
14
+ "pretraining_tp": 1,
15
+ "rms_norm_eps": 1e-06,
16
+ "rope_scaling": null,
17
+ "rope_theta": 10000.0,
18
+ "tie_word_embeddings": false,
19
+ "transformers_version": "4.28.1",
20
+ "use_cache": true,
21
+ "visual_config": {
22
+ "visual_hreducer": {
23
+ "_name_or_path": "",
24
+ "add_cross_attention": false,
25
+ "architectures": null,
26
+ "bad_words_ids": null,
27
+ "begin_suppress_tokens": null,
28
+ "bos_token_id": null,
29
+ "chunk_size_feed_forward": 0,
30
+ "conv_shape": "1x4",
31
+ "cross_attention_hidden_size": null,
32
+ "decoder_start_token_id": null,
33
+ "diversity_penalty": 0.0,
34
+ "do_sample": false,
35
+ "early_stopping": false,
36
+ "encoder_no_repeat_ngram_size": 0,
37
+ "eos_token_id": null,
38
+ "exponential_decay_length_penalty": null,
39
+ "finetuning_task": null,
40
+ "forced_bos_token_id": null,
41
+ "forced_eos_token_id": null,
42
+ "hidden_size": 1024,
43
+ "id2label": {
44
+ "0": "LABEL_0",
45
+ "1": "LABEL_1"
46
+ },
47
+ "initializer_range": 0.02,
48
+ "is_decoder": false,
49
+ "is_encoder_decoder": false,
50
+ "label2id": {
51
+ "LABEL_0": 0,
52
+ "LABEL_1": 1
53
+ },
54
+ "layer_norm_eps": 1e-06,
55
+ "length_penalty": 1.0,
56
+ "max_length": 20,
57
+ "min_length": 0,
58
+ "model_type": "mplug_docowl_hreducer",
59
+ "no_repeat_ngram_size": 0,
60
+ "num_beam_groups": 1,
61
+ "num_beams": 1,
62
+ "num_return_sequences": 1,
63
+ "output_attentions": false,
64
+ "output_hidden_states": false,
65
+ "output_scores": false,
66
+ "pad_token_id": null,
67
+ "prefix": null,
68
+ "problem_type": null,
69
+ "pruned_heads": {},
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": "4.28.1",
87
+ "typical_p": 1.0,
88
+ "use_bfloat16": false
89
+ },
90
+ "visual_model": {
91
+ "_name_or_path": "",
92
+ "add_cross_attention": false,
93
+ "architectures": null,
94
+ "attention_dropout": 0.0,
95
+ "bad_words_ids": null,
96
+ "begin_suppress_tokens": null,
97
+ "bos_token_id": null,
98
+ "chunk_size_feed_forward": 0,
99
+ "cross_attention_hidden_size": null,
100
+ "decoder_start_token_id": null,
101
+ "diversity_penalty": 0.0,
102
+ "do_sample": false,
103
+ "early_stopping": false,
104
+ "encoder_no_repeat_ngram_size": 0,
105
+ "eos_token_id": null,
106
+ "exponential_decay_length_penalty": null,
107
+ "finetuning_task": null,
108
+ "forced_bos_token_id": null,
109
+ "forced_eos_token_id": null,
110
+ "hidden_act": "quick_gelu",
111
+ "hidden_size": 1024,
112
+ "id2label": {
113
+ "0": "LABEL_0",
114
+ "1": "LABEL_1"
115
+ },
116
+ "image_size": 448,
117
+ "initializer_factor": 1.0,
118
+ "initializer_range": 0.02,
119
+ "intermediate_size": 4096,
120
+ "is_decoder": false,
121
+ "is_encoder_decoder": false,
122
+ "label2id": {
123
+ "LABEL_0": 0,
124
+ "LABEL_1": 1
125
+ },
126
+ "layer_norm_eps": 1e-06,
127
+ "length_penalty": 1.0,
128
+ "max_length": 20,
129
+ "min_length": 0,
130
+ "model_type": "mplug_owl_vision_model",
131
+ "no_repeat_ngram_size": 0,
132
+ "num_attention_heads": 16,
133
+ "num_beam_groups": 1,
134
+ "num_beams": 1,
135
+ "num_channels": 3,
136
+ "num_hidden_layers": 24,
137
+ "num_return_sequences": 1,
138
+ "output_attentions": false,
139
+ "output_hidden_states": false,
140
+ "output_scores": false,
141
+ "pad_token_id": null,
142
+ "patch_size": 14,
143
+ "prefix": null,
144
+ "problem_type": null,
145
+ "projection_dim": 768,
146
+ "pruned_heads": {},
147
+ "remove_invalid_values": false,
148
+ "repetition_penalty": 1.0,
149
+ "return_dict": true,
150
+ "return_dict_in_generate": false,
151
+ "sep_token_id": null,
152
+ "suppress_tokens": null,
153
+ "task_specific_params": null,
154
+ "temperature": 1.0,
155
+ "tf_legacy_loss": false,
156
+ "tie_encoder_decoder": false,
157
+ "tie_word_embeddings": true,
158
+ "tokenizer_class": null,
159
+ "top_k": 50,
160
+ "top_p": 1.0,
161
+ "torch_dtype": null,
162
+ "torchscript": false,
163
+ "transformers_version": "4.28.1",
164
+ "typical_p": 1.0,
165
+ "use_bfloat16": false,
166
+ "use_flash_attn": false
167
+ }
168
+ },
169
+ "vocab_size": 32000
170
+ }