Hugging Face's logo

brickerino
/
bc-val-2

Robotics
LeRobot
Safetensors
smolvla
Model card Files
xet
 Community
brickerino commited on
Commit
61b4a93
·
verified ·
1 Parent(s): c6435c0

Upload policy weights, train config and readme

Browse files
Files changed (4) hide show
  1. README.md +63 -0
  2. config.json +99 -0
  3. model.safetensors +3 -0
  4. train_config.json +318 -0
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: lerobot/smolvla_base
3
+ datasets: brickerino/blue-cube-train-90
4
+ library_name: lerobot
5
+ license: apache-2.0
6
+ model_name: smolvla
7
+ pipeline_tag: robotics
8
+ tags:
9
+ - robotics
10
+ - smolvla
11
+ - lerobot
12
+ ---
13
+
14
+ # Model Card for smolvla
15
+
16
+ <!-- Provide a quick summary of what the model is/does. -->
17
+
18
+
19
+ [SmolVLA](https://huggingface.co/papers/2506.01844) is a compact, efficient vision-language-action model that achieves competitive performance at reduced computational costs and can be deployed on consumer-grade hardware.
20
+
21
+
22
+ This policy has been trained and pushed to the Hub using [LeRobot](https://github.com/huggingface/lerobot).
23
+ See the full documentation at [LeRobot Docs](https://huggingface.co/docs/lerobot/index).
24
+
25
+ ---
26
+
27
+ ## How to Get Started with the Model
28
+
29
+ For a complete walkthrough, see the [training guide](https://huggingface.co/docs/lerobot/il_robots#train-a-policy).
30
+ Below is the short version on how to train and run inference/eval:
31
+
32
+ ### Train from scratch
33
+
34
+ ```bash
35
+ lerobot-train \
36
+ --dataset.repo_id=${HF_USER}/<dataset> \
37
+ --policy.type=act \
38
+ --output_dir=outputs/train/<desired_policy_repo_id> \
39
+ --job_name=lerobot_training \
40
+ --policy.device=cuda \
41
+ --policy.repo_id=${HF_USER}/<desired_policy_repo_id>
42
+ --wandb.enable=true
43
+ ```
44
+
45
+ _Writes checkpoints to `outputs/train/<desired_policy_repo_id>/checkpoints/`._
46
+
47
+ ### Evaluate the policy/run inference
48
+
49
+ ```bash
50
+ lerobot-record \
51
+ --robot.type=so100_follower \
52
+ --dataset.repo_id=<hf_user>/eval_<dataset> \
53
+ --policy.path=<hf_user>/<desired_policy_repo_id> \
54
+ --episodes=10
55
+ ```
56
+
57
+ Prefix the dataset repo with **eval\_** and supply `--policy.path` pointing to a local or hub checkpoint.
58
+
59
+ ---
60
+
61
+ ## Model Details
62
+
63
+ - **License:** apache-2.0
config.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "observation.images.camera3": {
28
+ "type": "VISUAL",
29
+ "shape": [
30
+ 3,
31
+ 256,
32
+ 256
33
+ ]
34
+ }
35
+ },
36
+ "output_features": {
37
+ "action": {
38
+ "type": "ACTION",
39
+ "shape": [
40
+ 6
41
+ ]
42
+ }
43
+ },
44
+ "device": "cuda",
45
+ "use_amp": false,
46
+ "use_peft": false,
47
+ "push_to_hub": true,
48
+ "repo_id": "brickerino/bc-val-2",
49
+ "private": null,
50
+ "tags": null,
51
+ "license": null,
52
+ "pretrained_path": "lerobot/smolvla_base",
53
+ "chunk_size": 50,
54
+ "n_action_steps": 50,
55
+ "normalization_mapping": {
56
+ "VISUAL": "IDENTITY",
57
+ "STATE": "MEAN_STD",
58
+ "ACTION": "MEAN_STD"
59
+ },
60
+ "max_state_dim": 32,
61
+ "max_action_dim": 32,
62
+ "resize_imgs_with_padding": [
63
+ 512,
64
+ 512
65
+ ],
66
+ "empty_cameras": 0,
67
+ "adapt_to_pi_aloha": false,
68
+ "use_delta_joint_actions_aloha": false,
69
+ "tokenizer_max_length": 48,
70
+ "num_steps": 10,
71
+ "use_cache": true,
72
+ "freeze_vision_encoder": true,
73
+ "train_expert_only": true,
74
+ "train_state_proj": true,
75
+ "optimizer_lr": 0.0001,
76
+ "optimizer_betas": [
77
+ 0.9,
78
+ 0.95
79
+ ],
80
+ "optimizer_eps": 1e-08,
81
+ "optimizer_weight_decay": 1e-10,
82
+ "optimizer_grad_clip_norm": 10.0,
83
+ "scheduler_warmup_steps": 1000,
84
+ "scheduler_decay_steps": 30000,
85
+ "scheduler_decay_lr": 2.5e-06,
86
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
87
+ "load_vlm_weights": true,
88
+ "add_image_special_tokens": false,
89
+ "attention_mode": "cross_attn",
90
+ "prefix_length": 0,
91
+ "pad_language_to": "max_length",
92
+ "num_expert_layers": 0,
93
+ "num_vlm_layers": 16,
94
+ "self_attn_every_n_layers": 2,
95
+ "expert_width_multiplier": 0.75,
96
+ "min_period": 0.004,
97
+ "max_period": 4.0,
98
+ "rtc_config": null
99
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d19fe669c0a39a09a83a9c1b3449a67d1b454e0194381a4e821a305753a49fd
3
+ size 906712520
train_config.json ADDED
@@ -0,0 +1,318 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "brickerino/blue-cube-train-90",
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": "torchcodec",
80
+ "streaming": false
81
+ },
82
+ "val_dataset": {
83
+ "repo_id": "brickerino/blue-cube-5",
84
+ "root": null,
85
+ "episodes": null,
86
+ "image_transforms": {
87
+ "enable": false,
88
+ "max_num_transforms": 3,
89
+ "random_order": false,
90
+ "tfs": {
91
+ "brightness": {
92
+ "weight": 1.0,
93
+ "type": "ColorJitter",
94
+ "kwargs": {
95
+ "brightness": [
96
+ 0.8,
97
+ 1.2
98
+ ]
99
+ }
100
+ },
101
+ "contrast": {
102
+ "weight": 1.0,
103
+ "type": "ColorJitter",
104
+ "kwargs": {
105
+ "contrast": [
106
+ 0.8,
107
+ 1.2
108
+ ]
109
+ }
110
+ },
111
+ "saturation": {
112
+ "weight": 1.0,
113
+ "type": "ColorJitter",
114
+ "kwargs": {
115
+ "saturation": [
116
+ 0.5,
117
+ 1.5
118
+ ]
119
+ }
120
+ },
121
+ "hue": {
122
+ "weight": 1.0,
123
+ "type": "ColorJitter",
124
+ "kwargs": {
125
+ "hue": [
126
+ -0.05,
127
+ 0.05
128
+ ]
129
+ }
130
+ },
131
+ "sharpness": {
132
+ "weight": 1.0,
133
+ "type": "SharpnessJitter",
134
+ "kwargs": {
135
+ "sharpness": [
136
+ 0.5,
137
+ 1.5
138
+ ]
139
+ }
140
+ },
141
+ "affine": {
142
+ "weight": 1.0,
143
+ "type": "RandomAffine",
144
+ "kwargs": {
145
+ "degrees": [
146
+ -5.0,
147
+ 5.0
148
+ ],
149
+ "translate": [
150
+ 0.05,
151
+ 0.05
152
+ ]
153
+ }
154
+ }
155
+ }
156
+ },
157
+ "revision": null,
158
+ "use_imagenet_stats": true,
159
+ "video_backend": "torchcodec",
160
+ "streaming": false
161
+ },
162
+ "env": null,
163
+ "policy": {
164
+ "type": "smolvla",
165
+ "n_obs_steps": 1,
166
+ "input_features": {
167
+ "observation.state": {
168
+ "type": "STATE",
169
+ "shape": [
170
+ 6
171
+ ]
172
+ },
173
+ "observation.images.camera1": {
174
+ "type": "VISUAL",
175
+ "shape": [
176
+ 3,
177
+ 256,
178
+ 256
179
+ ]
180
+ },
181
+ "observation.images.camera2": {
182
+ "type": "VISUAL",
183
+ "shape": [
184
+ 3,
185
+ 256,
186
+ 256
187
+ ]
188
+ },
189
+ "observation.images.camera3": {
190
+ "type": "VISUAL",
191
+ "shape": [
192
+ 3,
193
+ 256,
194
+ 256
195
+ ]
196
+ }
197
+ },
198
+ "output_features": {
199
+ "action": {
200
+ "type": "ACTION",
201
+ "shape": [
202
+ 6
203
+ ]
204
+ }
205
+ },
206
+ "device": "cuda",
207
+ "use_amp": false,
208
+ "use_peft": false,
209
+ "push_to_hub": true,
210
+ "repo_id": "brickerino/bc-val-2",
211
+ "private": null,
212
+ "tags": null,
213
+ "license": null,
214
+ "pretrained_path": "lerobot/smolvla_base",
215
+ "chunk_size": 50,
216
+ "n_action_steps": 50,
217
+ "normalization_mapping": {
218
+ "VISUAL": "IDENTITY",
219
+ "STATE": "MEAN_STD",
220
+ "ACTION": "MEAN_STD"
221
+ },
222
+ "max_state_dim": 32,
223
+ "max_action_dim": 32,
224
+ "resize_imgs_with_padding": [
225
+ 512,
226
+ 512
227
+ ],
228
+ "empty_cameras": 0,
229
+ "adapt_to_pi_aloha": false,
230
+ "use_delta_joint_actions_aloha": false,
231
+ "tokenizer_max_length": 48,
232
+ "num_steps": 10,
233
+ "use_cache": true,
234
+ "freeze_vision_encoder": true,
235
+ "train_expert_only": true,
236
+ "train_state_proj": true,
237
+ "optimizer_lr": 0.0001,
238
+ "optimizer_betas": [
239
+ 0.9,
240
+ 0.95
241
+ ],
242
+ "optimizer_eps": 1e-08,
243
+ "optimizer_weight_decay": 1e-10,
244
+ "optimizer_grad_clip_norm": 10.0,
245
+ "scheduler_warmup_steps": 1000,
246
+ "scheduler_decay_steps": 30000,
247
+ "scheduler_decay_lr": 2.5e-06,
248
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
249
+ "load_vlm_weights": true,
250
+ "add_image_special_tokens": false,
251
+ "attention_mode": "cross_attn",
252
+ "prefix_length": 0,
253
+ "pad_language_to": "max_length",
254
+ "num_expert_layers": 0,
255
+ "num_vlm_layers": 16,
256
+ "self_attn_every_n_layers": 2,
257
+ "expert_width_multiplier": 0.75,
258
+ "min_period": 0.004,
259
+ "max_period": 4.0,
260
+ "rtc_config": null
261
+ },
262
+ "output_dir": "outputs/train/bc-val-2",
263
+ "job_name": "bc-val",
264
+ "resume": false,
265
+ "seed": 1000,
266
+ "num_workers": 4,
267
+ "batch_size": 64,
268
+ "steps": 2000,
269
+ "eval_freq": 20000,
270
+ "log_freq": 200,
271
+ "tolerance_s": 0.0001,
272
+ "save_checkpoint": true,
273
+ "save_freq": 20000,
274
+ "use_policy_training_preset": true,
275
+ "optimizer": {
276
+ "type": "adamw",
277
+ "lr": 0.0001,
278
+ "weight_decay": 1e-10,
279
+ "grad_clip_norm": 10.0,
280
+ "betas": [
281
+ 0.9,
282
+ 0.95
283
+ ],
284
+ "eps": 1e-08
285
+ },
286
+ "scheduler": {
287
+ "type": "cosine_decay_with_warmup",
288
+ "num_warmup_steps": 1000,
289
+ "num_decay_steps": 30000,
290
+ "peak_lr": 0.0001,
291
+ "decay_lr": 2.5e-06
292
+ },
293
+ "eval": {
294
+ "n_episodes": 50,
295
+ "batch_size": 50,
296
+ "use_async_envs": false
297
+ },
298
+ "wandb": {
299
+ "enable": true,
300
+ "disable_artifact": false,
301
+ "project": "lerobot",
302
+ "entity": "sarath-chandar",
303
+ "notes": null,
304
+ "run_id": "by86shtn",
305
+ "mode": null
306
+ },
307
+ "peft": null,
308
+ "use_rabc": false,
309
+ "rabc_progress_path": null,
310
+ "rabc_kappa": 0.01,
311
+ "rabc_epsilon": 1e-06,
312
+ "rabc_head_mode": "sparse",
313
+ "rename_map": {
314
+ "observation.images.up": "observation.images.camera1",
315
+ "observation.images.wrist": "observation.images.camera2"
316
+ },
317
+ "checkpoint_path": null
318
+ }