mkche9/sponge_smolvla_v2
029
1{2 "name": "policy_preprocessor",3 "steps": [4 {5 "registry_name": "rename_observations_processor",6 "config": {7 "rename_map": {8 "observation.images.overhead": "observation.images.camera1",9 "observation.images.wrist": "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": null37 }38 },39 {40 "registry_name": "normalizer_processor",41 "config": {42 "eps": 1e-08,43 "features": {44 "observation.state": {45 "type": "STATE",46 "shape": [47 648 ]49 },50 "observation.images.camera1": {51 "type": "VISUAL",52 "shape": [53 3,54 256,55 25656 ]57 },58 "observation.images.camera2": {59 "type": "VISUAL",60 "shape": [61 3,62 256,63 25664 ]65 },66 "observation.images.camera3": {67 "type": "VISUAL",68 "shape": [69 3,70 256,71 25672 ]73 },74 "observation.images.empty_camera_0": {75 "type": "VISUAL",76 "shape": [77 3,78 480,79 64080 ]81 },82 "action": {83 "type": "ACTION",84 "shape": [85 686 ]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}