Hoshipu commited on
Commit
4739a4e
·
verified ·
1 Parent(s): cff42e1

Upload folder using huggingface_hub

Browse files
ckpt-200000/config.json ADDED
@@ -0,0 +1,258 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "action_mode": "auto",
3
+ "architectures": [
4
+ "XVLA"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "configuration_xvla.XVLAConfig",
8
+ "AutoModel": "modeling_xvla.XVLA"
9
+ },
10
+ "depth": 24,
11
+ "dim_time": 32,
12
+ "florence_config": {
13
+ "_attn_implementation_autoset": true,
14
+ "bos_token_id": 0,
15
+ "eos_token_id": 2,
16
+ "ignore_index": -100,
17
+ "is_encoder_decoder": true,
18
+ "model_type": "florence2",
19
+ "pad_token_id": 1,
20
+ "projection_dim": 1024,
21
+ "text_config": {
22
+ "_attn_implementation_autoset": true,
23
+ "_name_or_path": "",
24
+ "activation_dropout": 0.1,
25
+ "activation_function": "gelu",
26
+ "add_bias_logits": false,
27
+ "add_cross_attention": false,
28
+ "add_final_layer_norm": false,
29
+ "architectures": null,
30
+ "attention_dropout": 0.1,
31
+ "bad_words_ids": null,
32
+ "begin_suppress_tokens": null,
33
+ "bos_token_id": 0,
34
+ "chunk_size_feed_forward": 0,
35
+ "classif_dropout": 0.1,
36
+ "classifier_dropout": 0.0,
37
+ "cross_attention_hidden_size": null,
38
+ "d_model": 1024,
39
+ "decoder_attention_heads": 16,
40
+ "decoder_ffn_dim": 4096,
41
+ "decoder_layerdrop": 0.0,
42
+ "decoder_layers": 12,
43
+ "decoder_start_token_id": 2,
44
+ "diversity_penalty": 0.0,
45
+ "do_sample": false,
46
+ "dropout": 0.1,
47
+ "early_stopping": true,
48
+ "encoder_attention_heads": 16,
49
+ "encoder_ffn_dim": 4096,
50
+ "encoder_layerdrop": 0.0,
51
+ "encoder_layers": 12,
52
+ "encoder_no_repeat_ngram_size": 0,
53
+ "eos_token_id": 2,
54
+ "exponential_decay_length_penalty": null,
55
+ "finetuning_task": null,
56
+ "forced_bos_token_id": 0,
57
+ "forced_eos_token_id": 2,
58
+ "gradient_checkpointing": false,
59
+ "id2label": {
60
+ "0": "LABEL_0",
61
+ "1": "LABEL_1",
62
+ "2": "LABEL_2"
63
+ },
64
+ "init_std": 0.02,
65
+ "is_decoder": false,
66
+ "is_encoder_decoder": true,
67
+ "label2id": {
68
+ "LABEL_0": 0,
69
+ "LABEL_1": 1,
70
+ "LABEL_2": 2
71
+ },
72
+ "length_penalty": 1.0,
73
+ "max_length": 20,
74
+ "max_position_embeddings": 4096,
75
+ "min_length": 0,
76
+ "model_type": "florence2_language",
77
+ "no_repeat_ngram_size": 3,
78
+ "normalize_before": false,
79
+ "num_beam_groups": 1,
80
+ "num_beams": 3,
81
+ "num_hidden_layers": 12,
82
+ "num_return_sequences": 1,
83
+ "output_attentions": false,
84
+ "output_hidden_states": false,
85
+ "output_scores": false,
86
+ "pad_token_id": 1,
87
+ "prefix": null,
88
+ "problem_type": null,
89
+ "pruned_heads": {},
90
+ "remove_invalid_values": false,
91
+ "repetition_penalty": 1.0,
92
+ "return_dict": true,
93
+ "return_dict_in_generate": false,
94
+ "scale_embedding": false,
95
+ "sep_token_id": null,
96
+ "suppress_tokens": null,
97
+ "task_specific_params": null,
98
+ "temperature": 1.0,
99
+ "tf_legacy_loss": false,
100
+ "tie_encoder_decoder": false,
101
+ "tie_word_embeddings": true,
102
+ "tokenizer_class": null,
103
+ "top_k": 50,
104
+ "top_p": 1.0,
105
+ "torch_dtype": null,
106
+ "torchscript": false,
107
+ "typical_p": 1.0,
108
+ "use_bfloat16": false,
109
+ "use_cache": true,
110
+ "vocab_size": 51289
111
+ },
112
+ "torch_dtype": "float32",
113
+ "vision_config": {
114
+ "_attn_implementation_autoset": false,
115
+ "_name_or_path": "",
116
+ "add_cross_attention": false,
117
+ "architectures": null,
118
+ "bad_words_ids": null,
119
+ "begin_suppress_tokens": null,
120
+ "bos_token_id": null,
121
+ "chunk_size_feed_forward": 0,
122
+ "cross_attention_hidden_size": null,
123
+ "decoder_start_token_id": null,
124
+ "depths": [
125
+ 1,
126
+ 1,
127
+ 9,
128
+ 1
129
+ ],
130
+ "dim_embed": [
131
+ 256,
132
+ 512,
133
+ 1024,
134
+ 2048
135
+ ],
136
+ "diversity_penalty": 0.0,
137
+ "do_sample": false,
138
+ "drop_path_rate": 0.1,
139
+ "early_stopping": false,
140
+ "enable_checkpoint": false,
141
+ "encoder_no_repeat_ngram_size": 0,
142
+ "eos_token_id": null,
143
+ "exponential_decay_length_penalty": null,
144
+ "finetuning_task": null,
145
+ "forced_bos_token_id": null,
146
+ "forced_eos_token_id": null,
147
+ "id2label": {
148
+ "0": "LABEL_0",
149
+ "1": "LABEL_1"
150
+ },
151
+ "image_feature_source": [
152
+ "spatial_avg_pool",
153
+ "temporal_avg_pool"
154
+ ],
155
+ "image_pos_embed": {
156
+ "max_pos_embeddings": 50,
157
+ "type": "learned_abs_2d"
158
+ },
159
+ "is_decoder": false,
160
+ "is_encoder_decoder": false,
161
+ "label2id": {
162
+ "LABEL_0": 0,
163
+ "LABEL_1": 1
164
+ },
165
+ "length_penalty": 1.0,
166
+ "max_length": 20,
167
+ "min_length": 0,
168
+ "model_type": "davit",
169
+ "no_repeat_ngram_size": 0,
170
+ "num_beam_groups": 1,
171
+ "num_beams": 1,
172
+ "num_groups": [
173
+ 8,
174
+ 16,
175
+ 32,
176
+ 64
177
+ ],
178
+ "num_heads": [
179
+ 8,
180
+ 16,
181
+ 32,
182
+ 64
183
+ ],
184
+ "num_return_sequences": 1,
185
+ "output_attentions": false,
186
+ "output_hidden_states": false,
187
+ "output_scores": false,
188
+ "pad_token_id": null,
189
+ "patch_padding": [
190
+ 3,
191
+ 1,
192
+ 1,
193
+ 1
194
+ ],
195
+ "patch_prenorm": [
196
+ false,
197
+ true,
198
+ true,
199
+ true
200
+ ],
201
+ "patch_size": [
202
+ 7,
203
+ 3,
204
+ 3,
205
+ 3
206
+ ],
207
+ "patch_stride": [
208
+ 4,
209
+ 2,
210
+ 2,
211
+ 2
212
+ ],
213
+ "prefix": null,
214
+ "problem_type": null,
215
+ "projection_dim": 1024,
216
+ "pruned_heads": {},
217
+ "remove_invalid_values": false,
218
+ "repetition_penalty": 1.0,
219
+ "return_dict": true,
220
+ "return_dict_in_generate": false,
221
+ "sep_token_id": null,
222
+ "suppress_tokens": null,
223
+ "task_specific_params": null,
224
+ "temperature": 1.0,
225
+ "tf_legacy_loss": false,
226
+ "tie_encoder_decoder": false,
227
+ "tie_word_embeddings": true,
228
+ "tokenizer_class": null,
229
+ "top_k": 50,
230
+ "top_p": 1.0,
231
+ "torch_dtype": null,
232
+ "torchscript": false,
233
+ "typical_p": 1.0,
234
+ "use_bfloat16": false,
235
+ "visual_temporal_embedding": {
236
+ "max_temporal_embeddings": 100,
237
+ "type": "COSINE"
238
+ },
239
+ "window_size": 12
240
+ },
241
+ "vocab_size": 51289
242
+ },
243
+ "hidden_size": 1024,
244
+ "len_soft_prompts": 32,
245
+ "max_action_dim": 23,
246
+ "max_len_seq": 512,
247
+ "mlp_ratio": 4.0,
248
+ "model_type": "xvla",
249
+ "num_actions": 30,
250
+ "num_domains": 30,
251
+ "num_heads": 16,
252
+ "real_action_dim": 23,
253
+ "soft_prompt_length": 32,
254
+ "torch_dtype": "float32",
255
+ "transformers_version": "4.51.3",
256
+ "use_hetero_proj": false,
257
+ "use_proprio": true
258
+ }
ckpt-200000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
ckpt-200000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0b0d2740c6feb51a310206c742471f1ec43302570617982e4fde3fcb9fb80c1
3
+ size 3520174452
ckpt-200000/preprocessor_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_map": {
3
+ "AutoProcessor": "processing_xvla.XVLAProcessor"
4
+ },
5
+ "crop_size": {
6
+ "height": 224,
7
+ "width": 224
8
+ },
9
+ "do_center_crop": false,
10
+ "do_convert_rgb": null,
11
+ "do_normalize": true,
12
+ "do_rescale": true,
13
+ "do_resize": true,
14
+ "image_mean": [
15
+ 0.485,
16
+ 0.456,
17
+ 0.406
18
+ ],
19
+ "image_processor_type": "CLIPImageProcessor",
20
+ "image_std": [
21
+ 0.229,
22
+ 0.224,
23
+ 0.225
24
+ ],
25
+ "processor_class": "XVLAProcessor",
26
+ "resample": 3,
27
+ "rescale_factor": 0.00392156862745098,
28
+ "size": {
29
+ "height": 224,
30
+ "width": 224
31
+ }
32
+ }
ckpt-200000/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
ckpt-200000/state.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"global_step": 200000}
ckpt-200000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
ckpt-200000/tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 1024,
53
+ "pad_token": "<pad>",
54
+ "processor_class": "XVLAProcessor",
55
+ "sep_token": "</s>",
56
+ "tokenizer_class": "BartTokenizer",
57
+ "trim_offsets": true,
58
+ "unk_token": "<unk>"
59
+ }
ckpt-200000/vocab.json ADDED
The diff for this file is too large to render. See raw diff