zawnpn commited on
Commit
05dbefc
·
verified ·
1 Parent(s): c2ee1da

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,315 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "action_chunk_length": 16,
3
+ "action_dim": 13,
4
+ "downsample_ratio": 0.5,
5
+ "enable_robot_alignment": false,
6
+ "force_image_size": 448,
7
+ "gen_action_type": "prop_hidden",
8
+ "llm_config": {
9
+ "_attn_implementation_autoset": true,
10
+ "_name_or_path": "./pretrained/Qwen2.5-32B-Instruct",
11
+ "add_cross_attention": false,
12
+ "architectures": [
13
+ "Qwen2ForCausalLM"
14
+ ],
15
+ "attention_dropout": 0.0,
16
+ "attn_implementation": "flash_attention_2",
17
+ "bad_words_ids": null,
18
+ "begin_suppress_tokens": null,
19
+ "bos_token_id": 151643,
20
+ "chunk_size_feed_forward": 0,
21
+ "cross_attention_hidden_size": null,
22
+ "decoder_start_token_id": null,
23
+ "diversity_penalty": 0.0,
24
+ "do_sample": false,
25
+ "early_stopping": false,
26
+ "encoder_no_repeat_ngram_size": 0,
27
+ "eos_token_id": 151643,
28
+ "exponential_decay_length_penalty": null,
29
+ "finetuning_task": null,
30
+ "forced_bos_token_id": null,
31
+ "forced_eos_token_id": null,
32
+ "hidden_act": "silu",
33
+ "hidden_size": 3584,
34
+ "id2label": {
35
+ "0": "LABEL_0",
36
+ "1": "LABEL_1"
37
+ },
38
+ "initializer_range": 0.02,
39
+ "intermediate_size": 18944,
40
+ "is_decoder": false,
41
+ "is_encoder_decoder": false,
42
+ "label2id": {
43
+ "LABEL_0": 0,
44
+ "LABEL_1": 1
45
+ },
46
+ "length_penalty": 1.0,
47
+ "max_length": 20,
48
+ "max_position_embeddings": 32768,
49
+ "max_window_layers": 70,
50
+ "min_length": 0,
51
+ "model_type": "qwen2",
52
+ "moe_config": null,
53
+ "no_repeat_ngram_size": 0,
54
+ "num_attention_heads": 28,
55
+ "num_beam_groups": 1,
56
+ "num_beams": 1,
57
+ "num_hidden_layers": 28,
58
+ "num_key_value_heads": 4,
59
+ "num_return_sequences": 1,
60
+ "output_attentions": false,
61
+ "output_hidden_states": false,
62
+ "output_scores": false,
63
+ "pad_token_id": null,
64
+ "prefix": null,
65
+ "problem_type": null,
66
+ "pruned_heads": {},
67
+ "remove_invalid_values": false,
68
+ "repetition_penalty": 1.0,
69
+ "return_dict": true,
70
+ "return_dict_in_generate": false,
71
+ "rms_norm_eps": 1e-06,
72
+ "rope_scaling": {
73
+ "factor": 2.0,
74
+ "rope_type": "dynamic",
75
+ "type": "dynamic"
76
+ },
77
+ "rope_theta": 1000000.0,
78
+ "sep_token_id": null,
79
+ "sliding_window": null,
80
+ "suppress_tokens": null,
81
+ "task_specific_params": null,
82
+ "temperature": 1.0,
83
+ "tf_legacy_loss": false,
84
+ "tie_encoder_decoder": false,
85
+ "tie_word_embeddings": false,
86
+ "tokenizer_class": null,
87
+ "top_k": 50,
88
+ "top_p": 1.0,
89
+ "torch_dtype": "bfloat16",
90
+ "torchscript": false,
91
+ "transformers_version": "4.43.4",
92
+ "typical_p": 1.0,
93
+ "use_bfloat16": true,
94
+ "use_cache": false,
95
+ "use_sliding_window": false,
96
+ "vocab_size": 159869
97
+ },
98
+ "loss_func": "l1",
99
+ "model_type": "beingvla",
100
+ "motion_config": [
101
+ {
102
+ "activate": "relu",
103
+ "cache_path": null,
104
+ "chunk_size": 10,
105
+ "code_dim": 512,
106
+ "commit_weight": 0.02,
107
+ "depth": 3,
108
+ "depth_first": true,
109
+ "dilation_growth_rate": 1,
110
+ "down_t": 2,
111
+ "eval_window_size": 15,
112
+ "fps": 20,
113
+ "frame_interval": 2,
114
+ "instruction": null,
115
+ "is_hm3d_old": false,
116
+ "max_eval_motion_len": 80,
117
+ "max_motion_len": 200,
118
+ "max_text_len": 20,
119
+ "min_motion_len": 40,
120
+ "motion_code_path": "/share/dataset/Being-H0/vq_code_augv2/wrist_mano162_grvq_shared_w15_f2_c4096",
121
+ "motion_feat": "mano162",
122
+ "motion_feat_dir": null,
123
+ "motion_resume_pth": null,
124
+ "motion_unit_length": 4,
125
+ "mu": 0.99,
126
+ "multi_coords": true,
127
+ "nb_code": 4096,
128
+ "nb_joints": 22,
129
+ "new_token_type": "insert",
130
+ "norm": null,
131
+ "normalize": true,
132
+ "num_conv_layers": 3,
133
+ "num_quant_groups": 2,
134
+ "num_quantizers": 8,
135
+ "output_emb_width": 512,
136
+ "quantbeta": 1.0,
137
+ "quantizer_name": "group_residualvq",
138
+ "recons_loss": "l1_smooth",
139
+ "relative": true,
140
+ "seq_len": 64,
141
+ "shared_codebook": true,
142
+ "stride_t": 2,
143
+ "tmr_model_path": "",
144
+ "unit_length": 4,
145
+ "use_part": "wrist",
146
+ "val_split_file": "val/test.txt",
147
+ "vel_weight": 1.0,
148
+ "width": 512,
149
+ "window_size": 15
150
+ },
151
+ {
152
+ "activate": "relu",
153
+ "cache_path": null,
154
+ "chunk_size": 10,
155
+ "code_dim": 512,
156
+ "commit_weight": 0.02,
157
+ "depth": 3,
158
+ "depth_first": true,
159
+ "dilation_growth_rate": 1,
160
+ "down_t": 2,
161
+ "eval_window_size": 15,
162
+ "fps": 20,
163
+ "frame_interval": 2,
164
+ "instruction": null,
165
+ "is_hm3d_old": false,
166
+ "max_eval_motion_len": 80,
167
+ "max_motion_len": 200,
168
+ "max_text_len": 20,
169
+ "min_motion_len": 40,
170
+ "motion_code_path": "/share/dataset/Being-H0/vq_code_augv2/finger_mano162_grvq_shared_w15_f2_c4096",
171
+ "motion_feat": "mano162",
172
+ "motion_feat_dir": null,
173
+ "motion_resume_pth": null,
174
+ "motion_unit_length": 4,
175
+ "mu": 0.99,
176
+ "multi_coords": true,
177
+ "nb_code": 4096,
178
+ "nb_joints": 22,
179
+ "new_token_type": "insert",
180
+ "norm": null,
181
+ "normalize": true,
182
+ "num_conv_layers": 3,
183
+ "num_quant_groups": 2,
184
+ "num_quantizers": 8,
185
+ "output_emb_width": 512,
186
+ "quantbeta": 1.0,
187
+ "quantizer_name": "group_residualvq",
188
+ "recons_loss": "l1_smooth",
189
+ "relative": true,
190
+ "seq_len": 64,
191
+ "shared_codebook": true,
192
+ "stride_t": 2,
193
+ "tmr_model_path": "",
194
+ "unit_length": 4,
195
+ "use_part": "finger",
196
+ "val_split_file": "val/test.txt",
197
+ "vel_weight": 1.0,
198
+ "width": 512,
199
+ "window_size": 15
200
+ }
201
+ ],
202
+ "motion_type": "mano",
203
+ "proprio_dim": 13,
204
+ "ps_version": "v2",
205
+ "select_layer": -1,
206
+ "template": "internvl2_5",
207
+ "transformers_version": null,
208
+ "use_thumbnail": true,
209
+ "vision_config": {
210
+ "_attn_implementation_autoset": true,
211
+ "_name_or_path": "OpenGVLab/InternViT-6B-448px-V1-5",
212
+ "add_cross_attention": false,
213
+ "architectures": [
214
+ "InternVisionModel"
215
+ ],
216
+ "attention_dropout": 0.0,
217
+ "auto_map": {
218
+ "AutoConfig": "configuration_intern_vit.InternVisionConfig",
219
+ "AutoModel": "modeling_intern_vit.InternVisionModel"
220
+ },
221
+ "bad_words_ids": null,
222
+ "begin_suppress_tokens": null,
223
+ "bos_token_id": null,
224
+ "capacity_factor": 1.2,
225
+ "chunk_size_feed_forward": 0,
226
+ "cross_attention_hidden_size": null,
227
+ "decoder_start_token_id": null,
228
+ "diversity_penalty": 0.0,
229
+ "do_sample": false,
230
+ "drop_path_rate": 0.0,
231
+ "dropout": 0.0,
232
+ "early_stopping": false,
233
+ "encoder_no_repeat_ngram_size": 0,
234
+ "eos_token_id": null,
235
+ "eval_capacity_factor": 1.4,
236
+ "exponential_decay_length_penalty": null,
237
+ "finetuning_task": null,
238
+ "forced_bos_token_id": null,
239
+ "forced_eos_token_id": null,
240
+ "hidden_act": "gelu",
241
+ "hidden_size": 1024,
242
+ "id2label": {
243
+ "0": "LABEL_0",
244
+ "1": "LABEL_1"
245
+ },
246
+ "image_size": 448,
247
+ "initializer_factor": 0.1,
248
+ "initializer_range": 1e-10,
249
+ "intermediate_size": 4096,
250
+ "is_decoder": false,
251
+ "is_encoder_decoder": false,
252
+ "label2id": {
253
+ "LABEL_0": 0,
254
+ "LABEL_1": 1
255
+ },
256
+ "laux_allreduce": "all_nodes",
257
+ "layer_norm_eps": 1e-06,
258
+ "length_penalty": 1.0,
259
+ "max_length": 20,
260
+ "min_length": 0,
261
+ "model_type": "intern_vit_6b",
262
+ "moe_coeff_ratio": 0.5,
263
+ "moe_intermediate_size": 768,
264
+ "moe_output_scale": 4.0,
265
+ "no_repeat_ngram_size": 0,
266
+ "noisy_gate_policy": "RSample_before",
267
+ "norm_type": "layer_norm",
268
+ "num_attention_heads": 16,
269
+ "num_beam_groups": 1,
270
+ "num_beams": 1,
271
+ "num_channels": 3,
272
+ "num_experts": 8,
273
+ "num_hidden_layers": 24,
274
+ "num_return_sequences": 1,
275
+ "num_routed_experts": 4,
276
+ "num_shared_experts": 4,
277
+ "output_attentions": false,
278
+ "output_hidden_states": false,
279
+ "output_scores": false,
280
+ "pad_token_id": null,
281
+ "patch_size": 14,
282
+ "prefix": null,
283
+ "problem_type": null,
284
+ "pruned_heads": {},
285
+ "qk_normalization": false,
286
+ "qkv_bias": true,
287
+ "remove_invalid_values": false,
288
+ "repetition_penalty": 1.0,
289
+ "return_dict": true,
290
+ "return_dict_in_generate": false,
291
+ "sep_token_id": null,
292
+ "shared_expert_intermediate_size": 3072,
293
+ "suppress_tokens": null,
294
+ "task_specific_params": null,
295
+ "temperature": 1.0,
296
+ "tf_legacy_loss": false,
297
+ "tie_encoder_decoder": false,
298
+ "tie_word_embeddings": true,
299
+ "tokenizer_class": null,
300
+ "top_k": 50,
301
+ "top_p": 1.0,
302
+ "torch_dtype": "bfloat16",
303
+ "torchscript": false,
304
+ "transformers_version": "4.43.4",
305
+ "typical_p": 1.0,
306
+ "use_bfloat16": true,
307
+ "use_flash_attn": true,
308
+ "use_moe": false,
309
+ "use_residual": true,
310
+ "use_rts": false,
311
+ "use_weighted_residual": false
312
+ },
313
+ "vlm_config": {},
314
+ "vlm_type": "internvl"
315
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a45c4f3de29129418a505b0b16ae992451c6fcfe32c4b38ac966b0c10fed7208
3
+ size 5347150336
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1357bc020f78d987da618d46f200326664df4a29f900c5c27ddb1e52be7befee
3
+ size 5263095576
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6861737d19eb6263e6c2db2847def4918fe4a436ae7d3cdf1bb69191bda0207
3
+ size 5341020640
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a25e8f4c8f7409dc9b4c65c3e76a511496960d33431c1122966c5e3a32c5f072
3
+ size 500225052
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
vocab.json ADDED
The diff for this file is too large to render. See raw diff