Hugging Face's logo

binhpham
/
molmoact2-leslider

Robotics
Transformers
Safetensors
molmoact2
image-text-to-text
so100
so101
custom_code
Model card Files
xet
 Community
binhpham commited on
Commit
5033eb2
·
verified ·
1 Parent(s): 1a73cbe

Delete files model.safetensors.index.json policy_postprocessor.json policy_postprocessor_step_1_molmoact2_masked_unnormalizer.safetensors policy_preprocessor.json policy_preprocessor_step_2_molmoact2_masked_normalizer.safetensors train_config.json with huggingface_hub

Browse files
Files changed (6) hide show
  1. model.safetensors.index.json +0 -0
  2. policy_postprocessor.json +0 -36
  3. policy_postprocessor_step_1_molmoact2_masked_unnormalizer.safetensors +0 -3
  4. policy_preprocessor.json +0 -84
  5. policy_preprocessor_step_2_molmoact2_masked_normalizer.safetensors +0 -3
  6. train_config.json +0 -261
model.safetensors.index.json DELETED
The diff for this file is too large to render. See raw diff
 
policy_postprocessor.json DELETED
@@ -1,36 +0,0 @@
1
- {
2
- "name": "policy_postprocessor",
3
- "steps": [
4
- {
5
- "registry_name": "molmoact2_clamp_action",
6
- "config": {}
7
- },
8
- {
9
- "registry_name": "molmoact2_masked_unnormalizer",
10
- "config": {
11
- "eps": 1e-08,
12
- "features": {
13
- "action": {
14
- "type": "ACTION",
15
- "shape": [
16
- 6
17
- ]
18
- }
19
- },
20
- "norm_map": {
21
- "ACTION": "MEAN_STD",
22
- "STATE": "MEAN_STD",
23
- "VISUAL": "IDENTITY"
24
- }
25
- },
26
- "state_file": "policy_postprocessor_step_1_molmoact2_masked_unnormalizer.safetensors"
27
- },
28
- {
29
- "registry_name": "device_processor",
30
- "config": {
31
- "device": "cpu",
32
- "float_dtype": null
33
- }
34
- }
35
- ]
36
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
policy_postprocessor_step_1_molmoact2_masked_unnormalizer.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:780badc849565736586304325b0e42cf8836e31a49167815fec3bf122ef1db3a
3
- size 6640
 
 
 
 
policy_preprocessor.json DELETED
@@ -1,84 +0,0 @@
1
- {
2
- "name": "policy_preprocessor",
3
- "steps": [
4
- {
5
- "registry_name": "rename_observations_processor",
6
- "config": {
7
- "rename_map": {}
8
- }
9
- },
10
- {
11
- "registry_name": "to_batch_processor",
12
- "config": {}
13
- },
14
- {
15
- "registry_name": "molmoact2_masked_normalizer",
16
- "config": {
17
- "eps": 1e-08,
18
- "features": {
19
- "observation.state": {
20
- "type": "STATE",
21
- "shape": [
22
- 6
23
- ]
24
- },
25
- "observation.images.arm_camera": {
26
- "type": "VISUAL",
27
- "shape": [
28
- 3,
29
- 480,
30
- 640
31
- ]
32
- },
33
- "action": {
34
- "type": "ACTION",
35
- "shape": [
36
- 6
37
- ]
38
- }
39
- },
40
- "norm_map": {
41
- "ACTION": "MEAN_STD",
42
- "STATE": "MEAN_STD",
43
- "VISUAL": "IDENTITY"
44
- }
45
- },
46
- "state_file": "policy_preprocessor_step_2_molmoact2_masked_normalizer.safetensors"
47
- },
48
- {
49
- "registry_name": "molmoact2_clamp_normalized",
50
- "config": {}
51
- },
52
- {
53
- "registry_name": "molmoact2_pack_inputs",
54
- "config": {
55
- "checkpoint_path": "allenai/MolmoAct2-SO100_101",
56
- "checkpoint_revision": null,
57
- "checkpoint_force_download": false,
58
- "trust_remote_code": true,
59
- "action_mode": "continuous",
60
- "discrete_action_tokenizer": "allenai/MolmoAct2-FAST-Tokenizer",
61
- "image_keys": [
62
- "observation.images.arm_camera"
63
- ],
64
- "setup_type": "single so100/so101 robotic arm in molmoact2",
65
- "control_mode": "absolute joint pose",
66
- "normalize_language": true,
67
- "add_setup_tokens": true,
68
- "add_control_tokens": true,
69
- "num_state_tokens": 256,
70
- "max_sequence_length": null,
71
- "chunk_size": 30,
72
- "max_action_dim": 32,
73
- "env_action_dim": 6
74
- }
75
- },
76
- {
77
- "registry_name": "device_processor",
78
- "config": {
79
- "device": "cuda",
80
- "float_dtype": null
81
- }
82
- }
83
- ]
84
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
policy_preprocessor_step_2_molmoact2_masked_normalizer.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:780badc849565736586304325b0e42cf8836e31a49167815fec3bf122ef1db3a
3
- size 6640
 
 
 
 
train_config.json DELETED
@@ -1,261 +0,0 @@
1
- {
2
- "dataset": {
3
- "repo_id": "binhpham/spc-pick-stuff",
4
- "root": null,
5
- "episodes": null,
6
- "image_transforms": {
7
- "enable": true,
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
- "return_uint8": false,
81
- "streaming": false
82
- },
83
- "env": null,
84
- "policy": {
85
- "type": "molmoact2",
86
- "n_obs_steps": 1,
87
- "input_features": {
88
- "observation.state": {
89
- "type": "STATE",
90
- "shape": [
91
- 6
92
- ]
93
- },
94
- "observation.images.arm_camera": {
95
- "type": "VISUAL",
96
- "shape": [
97
- 3,
98
- 480,
99
- 640
100
- ]
101
- }
102
- },
103
- "output_features": {
104
- "action": {
105
- "type": "ACTION",
106
- "shape": [
107
- 6
108
- ]
109
- }
110
- },
111
- "device": "cuda",
112
- "use_amp": false,
113
- "use_peft": false,
114
- "push_to_hub": false,
115
- "repo_id": null,
116
- "private": null,
117
- "tags": null,
118
- "license": null,
119
- "pretrained_path": "/home/binhpham/outputs/molmoact2-leslider_steps10000_bs8_lr1e-5_chunk30/checkpoints/005000/pretrained_model",
120
- "checkpoint_path": "allenai/MolmoAct2-SO100_101",
121
- "checkpoint_revision": null,
122
- "checkpoint_force_download": false,
123
- "trust_remote_code": true,
124
- "chunk_size": 30,
125
- "n_action_steps": 30,
126
- "action_mode": "continuous",
127
- "inference_action_mode": null,
128
- "discrete_action_tokenizer": "allenai/MolmoAct2-FAST-Tokenizer",
129
- "discrete_generation_max_steps": null,
130
- "norm_tag": null,
131
- "setup_type": "single so100/so101 robotic arm in molmoact2",
132
- "control_mode": "absolute joint pose",
133
- "image_keys": [
134
- "observation.images.arm_camera"
135
- ],
136
- "normalize_language": true,
137
- "add_setup_tokens": true,
138
- "add_control_tokens": true,
139
- "normalize_gripper": false,
140
- "num_state_tokens": 256,
141
- "max_sequence_length": null,
142
- "expected_max_action_dim": 32,
143
- "num_flow_timesteps": 8,
144
- "flow_matching_cutoff": 1.0,
145
- "flow_matching_time_offset": 0.001,
146
- "flow_matching_time_scale": 0.999,
147
- "flow_matching_beta_alpha": 1.0,
148
- "flow_matching_beta_beta": 1.5,
149
- "num_inference_steps": null,
150
- "mask_action_dim_padding": true,
151
- "enable_inference_cuda_graph": true,
152
- "per_episode_seed": false,
153
- "eval_seed": null,
154
- "rtc_config": null,
155
- "enable_lora_vlm": false,
156
- "lora_rank": 64,
157
- "lora_alpha": 16,
158
- "lora_dropout": 0.05,
159
- "lora_bias": "none",
160
- "enable_lora_action_expert": false,
161
- "enable_knowledge_insulation": false,
162
- "freeze_embedding": true,
163
- "train_action_expert_only": false,
164
- "gradient_checkpointing": true,
165
- "model_dtype": "bfloat16",
166
- "softmax_auxiliary_loss": true,
167
- "softmax_auxiliary_loss_scale": 0.0001,
168
- "discrete_loss_token_weighting": "root_subsegments_root_tokens",
169
- "optimizer_lr": 1e-05,
170
- "optimizer_vit_lr": 5e-06,
171
- "optimizer_connector_lr": 5e-06,
172
- "optimizer_action_expert_lr": 5e-05,
173
- "optimizer_betas": [
174
- 0.9,
175
- 0.95
176
- ],
177
- "optimizer_eps": 1e-06,
178
- "optimizer_weight_decay": 0.0,
179
- "optimizer_grad_clip_norm": 1.0,
180
- "scheduler_warmup_steps": 200,
181
- "scheduler_decay_steps": null,
182
- "scheduler_decay_lr": 1e-06,
183
- "normalization_mapping": {
184
- "ACTION": "MEAN_STD",
185
- "STATE": "MEAN_STD",
186
- "VISUAL": "IDENTITY"
187
- },
188
- "dataset_feature_names": {
189
- "action": [
190
- "shoulder_pan.pos",
191
- "shoulder_lift.pos",
192
- "elbow_flex.pos",
193
- "wrist_flex.pos",
194
- "wrist_roll.pos",
195
- "gripper.pos"
196
- ],
197
- "observation.state": [
198
- "shoulder_pan.pos",
199
- "shoulder_lift.pos",
200
- "elbow_flex.pos",
201
- "wrist_flex.pos",
202
- "wrist_roll.pos",
203
- "gripper.pos"
204
- ]
205
- }
206
- },
207
- "reward_model": null,
208
- "output_dir": "/home/binhpham/outputs/molmoact2-leslider_steps10000_bs8_lr1e-5_chunk30",
209
- "job_name": "molmoact2",
210
- "resume": true,
211
- "seed": 1000,
212
- "cudnn_deterministic": false,
213
- "num_workers": 4,
214
- "batch_size": 8,
215
- "prefetch_factor": 4,
216
- "persistent_workers": true,
217
- "steps": 10000,
218
- "eval_freq": -1,
219
- "log_freq": 20,
220
- "tolerance_s": 0.5,
221
- "save_checkpoint": true,
222
- "save_freq": 2500,
223
- "use_policy_training_preset": true,
224
- "optimizer": {
225
- "type": "adamw",
226
- "lr": 1e-05,
227
- "weight_decay": 0.0,
228
- "grad_clip_norm": 1.0,
229
- "betas": [
230
- 0.9,
231
- 0.95
232
- ],
233
- "eps": 1e-06
234
- },
235
- "scheduler": {
236
- "type": "molmoact2_cosine_decay_with_warmup",
237
- "num_warmup_steps": 200,
238
- "num_decay_steps": null,
239
- "peak_lr": 1e-05,
240
- "decay_lr": 1e-06
241
- },
242
- "eval": {
243
- "n_episodes": 50,
244
- "batch_size": 11,
245
- "use_async_envs": true
246
- },
247
- "wandb": {
248
- "enable": false,
249
- "disable_artifact": false,
250
- "project": "lerobot",
251
- "entity": null,
252
- "notes": null,
253
- "run_id": null,
254
- "mode": null,
255
- "add_tags": true
256
- },
257
- "peft": null,
258
- "sample_weighting": null,
259
- "rename_map": {},
260
- "checkpoint_path": "/home/binhpham/outputs/molmoact2-leslider_steps10000_bs8_lr1e-5_chunk30/checkpoints/005000"
261
- }