hoangphu7122002ai commited on
Commit
f2a7a50
1 Parent(s): 66c9345

Training done

Browse files
Files changed (3) hide show
  1. config.json +182 -0
  2. generation_config.json +8 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,182 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "ef530ffa8ff545931fe09d80d5e05f914ed3305d",
3
+ "_name_or_path": "aravind-selvam/pix2struct_chart",
4
+ "architectures": [
5
+ "Pix2StructForConditionalGeneration"
6
+ ],
7
+ "decoder_end_token_id": 50349,
8
+ "decoder_start_token_id": 50344,
9
+ "eos_token_id": 1,
10
+ "initializer_factor": 1.0,
11
+ "initializer_range": 0.02,
12
+ "is_encoder_decoder": true,
13
+ "is_vqa": false,
14
+ "model_type": "pix2struct",
15
+ "pad_token_id": 0,
16
+ "text_config": {
17
+ "_name_or_path": "",
18
+ "add_cross_attention": false,
19
+ "architectures": null,
20
+ "bad_words_ids": null,
21
+ "begin_suppress_tokens": null,
22
+ "bos_token_id": null,
23
+ "chunk_size_feed_forward": 0,
24
+ "cross_attention_hidden_size": null,
25
+ "d_ff": 2048,
26
+ "d_kv": 64,
27
+ "decoder_start_token_id": 0,
28
+ "dense_act_fn": "gelu_new",
29
+ "diversity_penalty": 0.0,
30
+ "do_sample": false,
31
+ "dropout_rate": 0.2,
32
+ "early_stopping": false,
33
+ "encoder_hidden_size": 768,
34
+ "encoder_no_repeat_ngram_size": 0,
35
+ "eos_token_id": 1,
36
+ "exponential_decay_length_penalty": null,
37
+ "finetuning_task": null,
38
+ "forced_bos_token_id": null,
39
+ "forced_eos_token_id": null,
40
+ "hidden_size": 768,
41
+ "id2label": {
42
+ "0": "LABEL_0",
43
+ "1": "LABEL_1"
44
+ },
45
+ "initializer_factor": 1.0,
46
+ "initializer_range": 0.02,
47
+ "is_decoder": false,
48
+ "is_encoder_decoder": false,
49
+ "label2id": {
50
+ "LABEL_0": 0,
51
+ "LABEL_1": 1
52
+ },
53
+ "layer_norm_epsilon": 1e-06,
54
+ "length_penalty": 1.0,
55
+ "max_length": 20,
56
+ "min_length": 0,
57
+ "model_type": "pix2struct_text_model",
58
+ "no_repeat_ngram_size": 0,
59
+ "num_beam_groups": 1,
60
+ "num_beams": 1,
61
+ "num_heads": 12,
62
+ "num_layers": 12,
63
+ "num_return_sequences": 1,
64
+ "output_attentions": false,
65
+ "output_hidden_states": false,
66
+ "output_scores": false,
67
+ "pad_token_id": 0,
68
+ "prefix": null,
69
+ "problem_type": null,
70
+ "pruned_heads": {},
71
+ "relative_attention_max_distance": 128,
72
+ "relative_attention_num_buckets": 32,
73
+ "remove_invalid_values": false,
74
+ "repetition_penalty": 1.0,
75
+ "return_dict": true,
76
+ "return_dict_in_generate": false,
77
+ "sep_token_id": null,
78
+ "suppress_tokens": null,
79
+ "task_specific_params": null,
80
+ "temperature": 1.0,
81
+ "tf_legacy_loss": false,
82
+ "tie_encoder_decoder": false,
83
+ "tie_word_embeddings": false,
84
+ "tokenizer_class": null,
85
+ "top_k": 50,
86
+ "top_p": 1.0,
87
+ "torch_dtype": null,
88
+ "torchscript": false,
89
+ "transformers_version": "4.29.2",
90
+ "typical_p": 1.0,
91
+ "use_bfloat16": false,
92
+ "use_cache": false,
93
+ "vocab_size": 50353
94
+ },
95
+ "tie_word_embeddings": false,
96
+ "torch_dtype": "float32",
97
+ "transformers_version": null,
98
+ "vision_config": {
99
+ "_name_or_path": "",
100
+ "add_cross_attention": false,
101
+ "architectures": null,
102
+ "attention_dropout": 0.2,
103
+ "bad_words_ids": null,
104
+ "begin_suppress_tokens": null,
105
+ "bos_token_id": null,
106
+ "chunk_size_feed_forward": 0,
107
+ "cross_attention_hidden_size": null,
108
+ "d_ff": 2048,
109
+ "d_kv": 64,
110
+ "decoder_start_token_id": null,
111
+ "dense_act_fn": "gelu_new",
112
+ "diversity_penalty": 0.0,
113
+ "do_sample": false,
114
+ "dropout_rate": 0.2,
115
+ "early_stopping": false,
116
+ "encoder_no_repeat_ngram_size": 0,
117
+ "eos_token_id": null,
118
+ "exponential_decay_length_penalty": null,
119
+ "finetuning_task": null,
120
+ "forced_bos_token_id": null,
121
+ "forced_eos_token_id": null,
122
+ "hidden_dropout_prob": 0.2,
123
+ "hidden_size": 768,
124
+ "id2label": {
125
+ "0": "LABEL_0",
126
+ "1": "LABEL_1"
127
+ },
128
+ "initializer_factor": 1.0,
129
+ "initializer_range": 0.02,
130
+ "is_decoder": false,
131
+ "is_encoder_decoder": false,
132
+ "label2id": {
133
+ "LABEL_0": 0,
134
+ "LABEL_1": 1
135
+ },
136
+ "layer_norm_bias": false,
137
+ "layer_norm_eps": 1e-06,
138
+ "length_penalty": 1.0,
139
+ "max_length": 20,
140
+ "min_length": 0,
141
+ "model_type": "pix2struct_vision_model",
142
+ "no_repeat_ngram_size": 0,
143
+ "num_attention_heads": 12,
144
+ "num_beam_groups": 1,
145
+ "num_beams": 1,
146
+ "num_channels": 3,
147
+ "num_hidden_layers": 12,
148
+ "num_return_sequences": 1,
149
+ "output_attentions": false,
150
+ "output_hidden_states": false,
151
+ "output_scores": false,
152
+ "pad_token_id": null,
153
+ "patch_embed_hidden_size": 768,
154
+ "patch_size": 16,
155
+ "prefix": null,
156
+ "problem_type": null,
157
+ "projection_dim": 768,
158
+ "pruned_heads": {},
159
+ "relative_attention_max_distance": 128,
160
+ "relative_attention_num_buckets": 32,
161
+ "remove_invalid_values": false,
162
+ "repetition_penalty": 1.0,
163
+ "return_dict": true,
164
+ "return_dict_in_generate": false,
165
+ "sep_token_id": null,
166
+ "seq_len": 4096,
167
+ "suppress_tokens": null,
168
+ "task_specific_params": null,
169
+ "temperature": 1.0,
170
+ "tf_legacy_loss": false,
171
+ "tie_encoder_decoder": false,
172
+ "tie_word_embeddings": true,
173
+ "tokenizer_class": null,
174
+ "top_k": 50,
175
+ "top_p": 1.0,
176
+ "torch_dtype": null,
177
+ "torchscript": false,
178
+ "transformers_version": "4.29.2",
179
+ "typical_p": 1.0,
180
+ "use_bfloat16": false
181
+ }
182
+ }
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": "4.29.2",
7
+ "use_cache": false
8
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26ba39101bd7ef8a264a600d2d41debb4b9fee2854d7911ad79d019b2663c951
3
+ size 1129907777