Hugging Face's logo

AppliantRobotics
/
smolvla_merged_block

Safetensors
Model card Files
xet
 Community
AppliantRobotics commited on
Commit
5cee466
·
verified ·
1 Parent(s): 3527a72

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +94 -0
  2. model.safetensors +3 -0
  3. policy_postprocessor.json +32 -0
  4. policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  5. policy_preprocessor.json +90 -0
  6. policy_preprocessor_step_5_normalizer_processor.safetensors +3 -0
  7. train_config.json +250 -0
config.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "smolvla",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 6
9
+ ]
10
+ },
11
+ "observation.images.camera1": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 256,
16
+ 256
17
+ ]
18
+ },
19
+ "observation.images.camera2": {
20
+ "type": "VISUAL",
21
+ "shape": [
22
+ 3,
23
+ 256,
24
+ 256
25
+ ]
26
+ }
27
+ },
28
+ "output_features": {
29
+ "action": {
30
+ "type": "ACTION",
31
+ "shape": [
32
+ 6
33
+ ]
34
+ }
35
+ },
36
+ "device": "cuda",
37
+ "use_amp": false,
38
+ "use_peft": false,
39
+ "push_to_hub": false,
40
+ "repo_id": null,
41
+ "private": null,
42
+ "tags": null,
43
+ "license": null,
44
+ "pretrained_path": "lerobot/smolvla_base",
45
+ "pretrained_revision": null,
46
+ "chunk_size": 50,
47
+ "n_action_steps": 50,
48
+ "normalization_mapping": {
49
+ "VISUAL": "IDENTITY",
50
+ "STATE": "MEAN_STD",
51
+ "ACTION": "MEAN_STD"
52
+ },
53
+ "max_state_dim": 32,
54
+ "max_action_dim": 32,
55
+ "resize_imgs_with_padding": [
56
+ 512,
57
+ 512
58
+ ],
59
+ "empty_cameras": 0,
60
+ "adapt_to_pi_aloha": false,
61
+ "use_delta_joint_actions_aloha": false,
62
+ "tokenizer_max_length": 48,
63
+ "num_steps": 10,
64
+ "use_cache": true,
65
+ "freeze_vision_encoder": false,
66
+ "train_expert_only": false,
67
+ "train_state_proj": true,
68
+ "optimizer_lr": 0.0001,
69
+ "optimizer_betas": [
70
+ 0.9,
71
+ 0.95
72
+ ],
73
+ "optimizer_eps": 1e-08,
74
+ "optimizer_weight_decay": 1e-10,
75
+ "optimizer_grad_clip_norm": 10.0,
76
+ "scheduler_warmup_steps": 1000,
77
+ "scheduler_decay_steps": 30000,
78
+ "scheduler_decay_lr": 2.5e-06,
79
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
80
+ "load_vlm_weights": true,
81
+ "add_image_special_tokens": false,
82
+ "attention_mode": "cross_attn",
83
+ "prefix_length": 0,
84
+ "pad_language_to": "max_length",
85
+ "num_expert_layers": 0,
86
+ "num_vlm_layers": 16,
87
+ "self_attn_every_n_layers": 2,
88
+ "expert_width_multiplier": 0.75,
89
+ "min_period": 0.004,
90
+ "max_period": 4.0,
91
+ "rtc_config": null,
92
+ "compile_model": false,
93
+ "compile_mode": "max-autotune"
94
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63551cd24b4583f4b59c0b89e9d84e785d1c6c6f578cdf785f1d5e40832619fd
3
+ size 906712520
policy_postprocessor.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_postprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "unnormalizer_processor",
6
+ "config": {
7
+ "eps": 1e-08,
8
+ "features": {
9
+ "action": {
10
+ "type": "ACTION",
11
+ "shape": [
12
+ 6
13
+ ]
14
+ }
15
+ },
16
+ "norm_map": {
17
+ "VISUAL": "IDENTITY",
18
+ "STATE": "MEAN_STD",
19
+ "ACTION": "MEAN_STD"
20
+ }
21
+ },
22
+ "state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
23
+ },
24
+ {
25
+ "registry_name": "device_processor",
26
+ "config": {
27
+ "device": "cpu",
28
+ "float_dtype": null
29
+ }
30
+ }
31
+ ]
32
+ }
policy_postprocessor_step_0_unnormalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa177da0473e68b59651f1dc933a61793faf17f277978e1b3366f938c33a84fc
3
+ size 7672
policy_preprocessor.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_preprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "rename_observations_processor",
6
+ "config": {
7
+ "rename_map": {
8
+ "observation.images.Top camera": "observation.images.camera1",
9
+ "observation.images.Follower Cam": "observation.images.camera2"
10
+ }
11
+ }
12
+ },
13
+ {
14
+ "registry_name": "to_batch_processor",
15
+ "config": {}
16
+ },
17
+ {
18
+ "registry_name": "smolvla_new_line_processor",
19
+ "config": {}
20
+ },
21
+ {
22
+ "registry_name": "tokenizer_processor",
23
+ "config": {
24
+ "max_length": 48,
25
+ "task_key": "task",
26
+ "padding_side": "right",
27
+ "padding": "max_length",
28
+ "truncation": true,
29
+ "tokenizer_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct"
30
+ }
31
+ },
32
+ {
33
+ "registry_name": "device_processor",
34
+ "config": {
35
+ "device": "cuda",
36
+ "float_dtype": null
37
+ }
38
+ },
39
+ {
40
+ "registry_name": "normalizer_processor",
41
+ "config": {
42
+ "eps": 1e-08,
43
+ "features": {
44
+ "observation.state": {
45
+ "type": "STATE",
46
+ "shape": [
47
+ 6
48
+ ]
49
+ },
50
+ "observation.images.camera1": {
51
+ "type": "VISUAL",
52
+ "shape": [
53
+ 3,
54
+ 256,
55
+ 256
56
+ ]
57
+ },
58
+ "observation.images.camera2": {
59
+ "type": "VISUAL",
60
+ "shape": [
61
+ 3,
62
+ 256,
63
+ 256
64
+ ]
65
+ },
66
+ "observation.images.camera3": {
67
+ "type": "VISUAL",
68
+ "shape": [
69
+ 3,
70
+ 256,
71
+ 256
72
+ ]
73
+ },
74
+ "action": {
75
+ "type": "ACTION",
76
+ "shape": [
77
+ 6
78
+ ]
79
+ }
80
+ },
81
+ "norm_map": {
82
+ "VISUAL": "IDENTITY",
83
+ "STATE": "MEAN_STD",
84
+ "ACTION": "MEAN_STD"
85
+ }
86
+ },
87
+ "state_file": "policy_preprocessor_step_5_normalizer_processor.safetensors"
88
+ }
89
+ ]
90
+ }
policy_preprocessor_step_5_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa177da0473e68b59651f1dc933a61793faf17f277978e1b3366f938c33a84fc
3
+ size 7672
train_config.json ADDED
@@ -0,0 +1,250 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "AppliantRobotics/merged_block",
4
+ "root": null,
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": false,
8
+ "max_num_transforms": 3,
9
+ "random_order": false,
10
+ "tfs": {
11
+ "brightness": {
12
+ "weight": 1.0,
13
+ "type": "ColorJitter",
14
+ "kwargs": {
15
+ "brightness": [
16
+ 0.8,
17
+ 1.2
18
+ ]
19
+ }
20
+ },
21
+ "contrast": {
22
+ "weight": 1.0,
23
+ "type": "ColorJitter",
24
+ "kwargs": {
25
+ "contrast": [
26
+ 0.8,
27
+ 1.2
28
+ ]
29
+ }
30
+ },
31
+ "saturation": {
32
+ "weight": 1.0,
33
+ "type": "ColorJitter",
34
+ "kwargs": {
35
+ "saturation": [
36
+ 0.5,
37
+ 1.5
38
+ ]
39
+ }
40
+ },
41
+ "hue": {
42
+ "weight": 1.0,
43
+ "type": "ColorJitter",
44
+ "kwargs": {
45
+ "hue": [
46
+ -0.05,
47
+ 0.05
48
+ ]
49
+ }
50
+ },
51
+ "sharpness": {
52
+ "weight": 1.0,
53
+ "type": "SharpnessJitter",
54
+ "kwargs": {
55
+ "sharpness": [
56
+ 0.5,
57
+ 1.5
58
+ ]
59
+ }
60
+ },
61
+ "affine": {
62
+ "weight": 1.0,
63
+ "type": "RandomAffine",
64
+ "kwargs": {
65
+ "degrees": [
66
+ -5.0,
67
+ 5.0
68
+ ],
69
+ "translate": [
70
+ 0.05,
71
+ 0.05
72
+ ]
73
+ }
74
+ }
75
+ }
76
+ },
77
+ "revision": null,
78
+ "use_imagenet_stats": true,
79
+ "video_backend": "pyav",
80
+ "return_uint8": false,
81
+ "depth_output_unit": "mm",
82
+ "streaming": false,
83
+ "eval_split": 0.0
84
+ },
85
+ "env": null,
86
+ "policy": {
87
+ "type": "smolvla",
88
+ "n_obs_steps": 1,
89
+ "input_features": {
90
+ "observation.state": {
91
+ "type": "STATE",
92
+ "shape": [
93
+ 6
94
+ ]
95
+ },
96
+ "observation.images.camera1": {
97
+ "type": "VISUAL",
98
+ "shape": [
99
+ 3,
100
+ 256,
101
+ 256
102
+ ]
103
+ },
104
+ "observation.images.camera2": {
105
+ "type": "VISUAL",
106
+ "shape": [
107
+ 3,
108
+ 256,
109
+ 256
110
+ ]
111
+ }
112
+ },
113
+ "output_features": {
114
+ "action": {
115
+ "type": "ACTION",
116
+ "shape": [
117
+ 6
118
+ ]
119
+ }
120
+ },
121
+ "device": "cuda",
122
+ "use_amp": false,
123
+ "use_peft": false,
124
+ "push_to_hub": false,
125
+ "repo_id": null,
126
+ "private": null,
127
+ "tags": null,
128
+ "license": null,
129
+ "pretrained_path": "lerobot/smolvla_base",
130
+ "pretrained_revision": null,
131
+ "chunk_size": 50,
132
+ "n_action_steps": 50,
133
+ "normalization_mapping": {
134
+ "VISUAL": "IDENTITY",
135
+ "STATE": "MEAN_STD",
136
+ "ACTION": "MEAN_STD"
137
+ },
138
+ "max_state_dim": 32,
139
+ "max_action_dim": 32,
140
+ "resize_imgs_with_padding": [
141
+ 512,
142
+ 512
143
+ ],
144
+ "empty_cameras": 0,
145
+ "adapt_to_pi_aloha": false,
146
+ "use_delta_joint_actions_aloha": false,
147
+ "tokenizer_max_length": 48,
148
+ "num_steps": 10,
149
+ "use_cache": true,
150
+ "freeze_vision_encoder": false,
151
+ "train_expert_only": false,
152
+ "train_state_proj": true,
153
+ "optimizer_lr": 0.0001,
154
+ "optimizer_betas": [
155
+ 0.9,
156
+ 0.95
157
+ ],
158
+ "optimizer_eps": 1e-08,
159
+ "optimizer_weight_decay": 1e-10,
160
+ "optimizer_grad_clip_norm": 10.0,
161
+ "scheduler_warmup_steps": 1000,
162
+ "scheduler_decay_steps": 30000,
163
+ "scheduler_decay_lr": 2.5e-06,
164
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
165
+ "load_vlm_weights": true,
166
+ "add_image_special_tokens": false,
167
+ "attention_mode": "cross_attn",
168
+ "prefix_length": 0,
169
+ "pad_language_to": "max_length",
170
+ "num_expert_layers": 0,
171
+ "num_vlm_layers": 16,
172
+ "self_attn_every_n_layers": 2,
173
+ "expert_width_multiplier": 0.75,
174
+ "min_period": 0.004,
175
+ "max_period": 4.0,
176
+ "rtc_config": null,
177
+ "compile_model": false,
178
+ "compile_mode": "max-autotune"
179
+ },
180
+ "reward_model": null,
181
+ "output_dir": "outputs\\train\\smolvla_merged_block",
182
+ "job_name": "smolvla_merged_block",
183
+ "resume": false,
184
+ "seed": 1000,
185
+ "cudnn_deterministic": false,
186
+ "num_workers": 4,
187
+ "batch_size": 16,
188
+ "prefetch_factor": 4,
189
+ "persistent_workers": true,
190
+ "steps": 20000,
191
+ "env_eval_freq": 20000,
192
+ "log_freq": 200,
193
+ "eval_steps": 0,
194
+ "max_eval_samples": 0,
195
+ "tolerance_s": 0.0001,
196
+ "save_checkpoint": true,
197
+ "save_freq": 20000,
198
+ "use_policy_training_preset": true,
199
+ "optimizer": {
200
+ "type": "adamw",
201
+ "lr": 0.0001,
202
+ "weight_decay": 1e-10,
203
+ "grad_clip_norm": 10.0,
204
+ "betas": [
205
+ 0.9,
206
+ 0.95
207
+ ],
208
+ "eps": 1e-08
209
+ },
210
+ "scheduler": {
211
+ "type": "cosine_decay_with_warmup",
212
+ "num_warmup_steps": 1000,
213
+ "num_decay_steps": 30000,
214
+ "peak_lr": 0.0001,
215
+ "decay_lr": 2.5e-06
216
+ },
217
+ "eval": {
218
+ "n_episodes": 50,
219
+ "batch_size": 16,
220
+ "use_async_envs": true,
221
+ "recording": false,
222
+ "recording_repo_id": null,
223
+ "recording_private": false
224
+ },
225
+ "wandb": {
226
+ "enable": false,
227
+ "disable_artifact": false,
228
+ "project": "lerobot",
229
+ "entity": null,
230
+ "notes": null,
231
+ "run_id": null,
232
+ "mode": null,
233
+ "add_tags": true
234
+ },
235
+ "peft": null,
236
+ "job": {
237
+ "target": null,
238
+ "image": "huggingface/lerobot-gpu:latest",
239
+ "timeout": "2d",
240
+ "detach": false,
241
+ "tags": []
242
+ },
243
+ "save_checkpoint_to_hub": false,
244
+ "sample_weighting": null,
245
+ "rename_map": {
246
+ "observation.images.Top camera": "observation.images.camera1",
247
+ "observation.images.Follower Cam": "observation.images.camera2"
248
+ },
249
+ "checkpoint_path": null
250
+ }