initial commit
Browse files- config.json +181 -0
- generation_config.json +8 -0
- preprocessor_config.json +12 -0
- special_tokens_map.json +107 -0
- tokenizer.json +0 -0
- tokenizer_config.json +114 -0
config.json
ADDED
@@ -0,0 +1,181 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_commit_hash": "956e2761626d0c37672c7741204a105ecd389245",
|
3 |
+
"_name_or_path": "google/pix2struct-base",
|
4 |
+
"architectures": [
|
5 |
+
"Pix2StructForConditionalGeneration"
|
6 |
+
],
|
7 |
+
"decoder_start_token_id": 0,
|
8 |
+
"eos_token_id": 1,
|
9 |
+
"initializer_factor": 1.0,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"is_encoder_decoder": true,
|
12 |
+
"is_vqa": false,
|
13 |
+
"model_type": "pix2struct",
|
14 |
+
"pad_token_id": 0,
|
15 |
+
"text_config": {
|
16 |
+
"_name_or_path": "",
|
17 |
+
"add_cross_attention": false,
|
18 |
+
"architectures": null,
|
19 |
+
"bad_words_ids": null,
|
20 |
+
"begin_suppress_tokens": null,
|
21 |
+
"bos_token_id": null,
|
22 |
+
"chunk_size_feed_forward": 0,
|
23 |
+
"cross_attention_hidden_size": null,
|
24 |
+
"d_ff": 2048,
|
25 |
+
"d_kv": 64,
|
26 |
+
"decoder_start_token_id": 0,
|
27 |
+
"dense_act_fn": "gelu_new",
|
28 |
+
"diversity_penalty": 0.0,
|
29 |
+
"do_sample": false,
|
30 |
+
"dropout_rate": 0.2,
|
31 |
+
"early_stopping": false,
|
32 |
+
"encoder_hidden_size": 768,
|
33 |
+
"encoder_no_repeat_ngram_size": 0,
|
34 |
+
"eos_token_id": 1,
|
35 |
+
"exponential_decay_length_penalty": null,
|
36 |
+
"finetuning_task": null,
|
37 |
+
"forced_bos_token_id": null,
|
38 |
+
"forced_eos_token_id": null,
|
39 |
+
"hidden_size": 768,
|
40 |
+
"id2label": {
|
41 |
+
"0": "LABEL_0",
|
42 |
+
"1": "LABEL_1"
|
43 |
+
},
|
44 |
+
"initializer_factor": 1.0,
|
45 |
+
"initializer_range": 0.02,
|
46 |
+
"is_decoder": true,
|
47 |
+
"is_encoder_decoder": false,
|
48 |
+
"label2id": {
|
49 |
+
"LABEL_0": 0,
|
50 |
+
"LABEL_1": 1
|
51 |
+
},
|
52 |
+
"layer_norm_epsilon": 1e-06,
|
53 |
+
"length_penalty": 1.0,
|
54 |
+
"max_length": 20,
|
55 |
+
"min_length": 0,
|
56 |
+
"model_type": "pix2struct_text_model",
|
57 |
+
"no_repeat_ngram_size": 0,
|
58 |
+
"num_beam_groups": 1,
|
59 |
+
"num_beams": 1,
|
60 |
+
"num_heads": 12,
|
61 |
+
"num_layers": 12,
|
62 |
+
"num_return_sequences": 1,
|
63 |
+
"output_attentions": false,
|
64 |
+
"output_hidden_states": false,
|
65 |
+
"output_scores": false,
|
66 |
+
"pad_token_id": 0,
|
67 |
+
"prefix": null,
|
68 |
+
"problem_type": null,
|
69 |
+
"pruned_heads": {},
|
70 |
+
"relative_attention_max_distance": 128,
|
71 |
+
"relative_attention_num_buckets": 32,
|
72 |
+
"remove_invalid_values": false,
|
73 |
+
"repetition_penalty": 1.0,
|
74 |
+
"return_dict": true,
|
75 |
+
"return_dict_in_generate": false,
|
76 |
+
"sep_token_id": null,
|
77 |
+
"suppress_tokens": null,
|
78 |
+
"task_specific_params": null,
|
79 |
+
"temperature": 1.0,
|
80 |
+
"tf_legacy_loss": false,
|
81 |
+
"tie_encoder_decoder": false,
|
82 |
+
"tie_word_embeddings": false,
|
83 |
+
"tokenizer_class": null,
|
84 |
+
"top_k": 50,
|
85 |
+
"top_p": 1.0,
|
86 |
+
"torch_dtype": null,
|
87 |
+
"torchscript": false,
|
88 |
+
"transformers_version": "4.30.2",
|
89 |
+
"typical_p": 1.0,
|
90 |
+
"use_bfloat16": false,
|
91 |
+
"use_cache": false,
|
92 |
+
"vocab_size": 50244
|
93 |
+
},
|
94 |
+
"tie_word_embeddings": false,
|
95 |
+
"torch_dtype": "float32",
|
96 |
+
"transformers_version": null,
|
97 |
+
"vision_config": {
|
98 |
+
"_name_or_path": "",
|
99 |
+
"add_cross_attention": false,
|
100 |
+
"architectures": null,
|
101 |
+
"attention_dropout": 0.2,
|
102 |
+
"bad_words_ids": null,
|
103 |
+
"begin_suppress_tokens": null,
|
104 |
+
"bos_token_id": null,
|
105 |
+
"chunk_size_feed_forward": 0,
|
106 |
+
"cross_attention_hidden_size": null,
|
107 |
+
"d_ff": 2048,
|
108 |
+
"d_kv": 64,
|
109 |
+
"decoder_start_token_id": null,
|
110 |
+
"dense_act_fn": "gelu_new",
|
111 |
+
"diversity_penalty": 0.0,
|
112 |
+
"do_sample": false,
|
113 |
+
"dropout_rate": 0.2,
|
114 |
+
"early_stopping": false,
|
115 |
+
"encoder_no_repeat_ngram_size": 0,
|
116 |
+
"eos_token_id": null,
|
117 |
+
"exponential_decay_length_penalty": null,
|
118 |
+
"finetuning_task": null,
|
119 |
+
"forced_bos_token_id": null,
|
120 |
+
"forced_eos_token_id": null,
|
121 |
+
"hidden_dropout_prob": 0.2,
|
122 |
+
"hidden_size": 768,
|
123 |
+
"id2label": {
|
124 |
+
"0": "LABEL_0",
|
125 |
+
"1": "LABEL_1"
|
126 |
+
},
|
127 |
+
"initializer_factor": 1.0,
|
128 |
+
"initializer_range": 0.02,
|
129 |
+
"is_decoder": false,
|
130 |
+
"is_encoder_decoder": false,
|
131 |
+
"label2id": {
|
132 |
+
"LABEL_0": 0,
|
133 |
+
"LABEL_1": 1
|
134 |
+
},
|
135 |
+
"layer_norm_bias": false,
|
136 |
+
"layer_norm_eps": 1e-06,
|
137 |
+
"length_penalty": 1.0,
|
138 |
+
"max_length": 20,
|
139 |
+
"min_length": 0,
|
140 |
+
"model_type": "pix2struct_vision_model",
|
141 |
+
"no_repeat_ngram_size": 0,
|
142 |
+
"num_attention_heads": 12,
|
143 |
+
"num_beam_groups": 1,
|
144 |
+
"num_beams": 1,
|
145 |
+
"num_channels": 3,
|
146 |
+
"num_hidden_layers": 12,
|
147 |
+
"num_return_sequences": 1,
|
148 |
+
"output_attentions": false,
|
149 |
+
"output_hidden_states": false,
|
150 |
+
"output_scores": false,
|
151 |
+
"pad_token_id": null,
|
152 |
+
"patch_embed_hidden_size": 768,
|
153 |
+
"patch_size": 16,
|
154 |
+
"prefix": null,
|
155 |
+
"problem_type": null,
|
156 |
+
"projection_dim": 768,
|
157 |
+
"pruned_heads": {},
|
158 |
+
"relative_attention_max_distance": 128,
|
159 |
+
"relative_attention_num_buckets": 32,
|
160 |
+
"remove_invalid_values": false,
|
161 |
+
"repetition_penalty": 1.0,
|
162 |
+
"return_dict": true,
|
163 |
+
"return_dict_in_generate": false,
|
164 |
+
"sep_token_id": null,
|
165 |
+
"seq_len": 4096,
|
166 |
+
"suppress_tokens": null,
|
167 |
+
"task_specific_params": null,
|
168 |
+
"temperature": 1.0,
|
169 |
+
"tf_legacy_loss": false,
|
170 |
+
"tie_encoder_decoder": false,
|
171 |
+
"tie_word_embeddings": true,
|
172 |
+
"tokenizer_class": null,
|
173 |
+
"top_k": 50,
|
174 |
+
"top_p": 1.0,
|
175 |
+
"torch_dtype": null,
|
176 |
+
"torchscript": false,
|
177 |
+
"transformers_version": "4.30.2",
|
178 |
+
"typical_p": 1.0,
|
179 |
+
"use_bfloat16": false
|
180 |
+
}
|
181 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "4.30.2",
|
7 |
+
"use_cache": false
|
8 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_convert_rgb": true,
|
3 |
+
"do_normalize": true,
|
4 |
+
"image_processor_type": "Pix2StructImageProcessor",
|
5 |
+
"is_vqa": false,
|
6 |
+
"max_patches": 2048,
|
7 |
+
"patch_size": {
|
8 |
+
"height": 16,
|
9 |
+
"width": 16
|
10 |
+
},
|
11 |
+
"processor_class": "Pix2StructProcessor"
|
12 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
],
|
104 |
+
"eos_token": "</s>",
|
105 |
+
"pad_token": "<pad>",
|
106 |
+
"unk_token": "<unk>"
|
107 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
],
|
104 |
+
"clean_up_tokenization_spaces": true,
|
105 |
+
"eos_token": "</s>",
|
106 |
+
"extra_ids": 100,
|
107 |
+
"model_max_length": 1000000000000000019884624838656,
|
108 |
+
"pad_token": "<pad>",
|
109 |
+
"processor_class": "Pix2StructProcessor",
|
110 |
+
"sp_model_kwargs": {},
|
111 |
+
"tokenizer_class": "T5Tokenizer",
|
112 |
+
"trust_remote_code": false,
|
113 |
+
"unk_token": "<unk>"
|
114 |
+
}
|