Hugging Face's logo

ImKyungjin
/
smolvla-stackcube-v4-10k

Safetensors
Model card Files
xet
 Community
ImKyungjin commited on
Commit
b3d9539
·
verified ·
1 Parent(s): 181a1a4

SmolVLA stackcube_v4 finetune, 10k steps, batch 64

Browse files
Files changed (6) hide show
  1. config.json +109 -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 +98 -0
  6. policy_preprocessor_step_5_normalizer_processor.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "observation.images.empty_camera_0": {
36
+ "type": "VISUAL",
37
+ "shape": [
38
+ 3,
39
+ 480,
40
+ 640
41
+ ]
42
+ }
43
+ },
44
+ "output_features": {
45
+ "action": {
46
+ "type": "ACTION",
47
+ "shape": [
48
+ 6
49
+ ]
50
+ }
51
+ },
52
+ "device": "cuda",
53
+ "use_amp": false,
54
+ "use_peft": false,
55
+ "push_to_hub": true,
56
+ "repo_id": "ImKyungjin/smolvla-stackcube-v4",
57
+ "private": false,
58
+ "tags": null,
59
+ "license": null,
60
+ "pretrained_path": "lerobot/smolvla_base",
61
+ "chunk_size": 50,
62
+ "n_action_steps": 50,
63
+ "normalization_mapping": {
64
+ "VISUAL": "IDENTITY",
65
+ "STATE": "MEAN_STD",
66
+ "ACTION": "MEAN_STD"
67
+ },
68
+ "max_state_dim": 32,
69
+ "max_action_dim": 32,
70
+ "resize_imgs_with_padding": [
71
+ 512,
72
+ 512
73
+ ],
74
+ "empty_cameras": 1,
75
+ "adapt_to_pi_aloha": false,
76
+ "use_delta_joint_actions_aloha": false,
77
+ "tokenizer_max_length": 48,
78
+ "num_steps": 10,
79
+ "use_cache": true,
80
+ "freeze_vision_encoder": true,
81
+ "train_expert_only": true,
82
+ "train_state_proj": true,
83
+ "optimizer_lr": 0.0001,
84
+ "optimizer_betas": [
85
+ 0.9,
86
+ 0.95
87
+ ],
88
+ "optimizer_eps": 1e-08,
89
+ "optimizer_weight_decay": 1e-10,
90
+ "optimizer_grad_clip_norm": 10.0,
91
+ "scheduler_warmup_steps": 1000,
92
+ "scheduler_decay_steps": 30000,
93
+ "scheduler_decay_lr": 2.5e-06,
94
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
95
+ "load_vlm_weights": true,
96
+ "add_image_special_tokens": false,
97
+ "attention_mode": "cross_attn",
98
+ "prefix_length": 0,
99
+ "pad_language_to": "max_length",
100
+ "num_expert_layers": 0,
101
+ "num_vlm_layers": 16,
102
+ "self_attn_every_n_layers": 2,
103
+ "expert_width_multiplier": 0.75,
104
+ "min_period": 0.004,
105
+ "max_period": 4.0,
106
+ "rtc_config": null,
107
+ "compile_model": false,
108
+ "compile_mode": "max-autotune"
109
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60fe3c2b805394e63db740f592f73e6b8a57ccc3c596c230a9bb2cfd2e685952
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 sha256:05517968329aedf5b911251710e05bb2194fbb29bf6511baa070a849e99fcd10
3
+ size 7536
policy_preprocessor.json ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_preprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "rename_observations_processor",
6
+ "config": {
7
+ "rename_map": {
8
+ "observation.images.top": "observation.images.camera1",
9
+ "observation.images.front": "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
+ "observation.images.empty_camera_0": {
75
+ "type": "VISUAL",
76
+ "shape": [
77
+ 3,
78
+ 480,
79
+ 640
80
+ ]
81
+ },
82
+ "action": {
83
+ "type": "ACTION",
84
+ "shape": [
85
+ 6
86
+ ]
87
+ }
88
+ },
89
+ "norm_map": {
90
+ "VISUAL": "IDENTITY",
91
+ "STATE": "MEAN_STD",
92
+ "ACTION": "MEAN_STD"
93
+ }
94
+ },
95
+ "state_file": "policy_preprocessor_step_5_normalizer_processor.safetensors"
96
+ }
97
+ ]
98
+ }
policy_preprocessor_step_5_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05517968329aedf5b911251710e05bb2194fbb29bf6511baa070a849e99fcd10
3
+ size 7536