Upload policy weights, train config and readme

README.md

@@ -0,0 +1,62 @@
+---
+datasets: HuggingFaceVLA/libero
+library_name: lerobot
+license: apache-2.0
+model_name: vla0
+pipeline_tag: robotics
+tags:
+- lerobot
+- robotics
+- vla0
+---
+
+# Model Card for vla0
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+_Model type not recognized — please update this template._
+
+
+This policy has been trained and pushed to the Hub using [LeRobot](https://github.com/huggingface/lerobot).
+See the full documentation at [LeRobot Docs](https://huggingface.co/docs/lerobot/index).
+
+---
+
+## How to Get Started with the Model
+
+For a complete walkthrough, see the [training guide](https://huggingface.co/docs/lerobot/il_robots#train-a-policy).
+Below is the short version on how to train and run inference/eval:
+
+### Train from scratch
+
+```bash
+lerobot-train \
+  --dataset.repo_id=${HF_USER}/<dataset> \
+  --policy.type=act \
+  --output_dir=outputs/train/<desired_policy_repo_id> \
+  --job_name=lerobot_training \
+  --policy.device=cuda \
+  --policy.repo_id=${HF_USER}/<desired_policy_repo_id>
+  --wandb.enable=true
+```
+
+_Writes checkpoints to `outputs/train/<desired_policy_repo_id>/checkpoints/`._
+
+### Evaluate the policy/run inference
+
+```bash
+lerobot-record \
+  --robot.type=so100_follower \
+  --dataset.repo_id=<hf_user>/eval_<dataset> \
+  --policy.path=<hf_user>/<desired_policy_repo_id> \
+  --episodes=10
+```
+
+Prefix the dataset repo with **eval\_** and supply `--policy.path` pointing to a local or hub checkpoint.
+
+---
+
+## Model Details
+
+- **License:** apache-2.0

config.json

@@ -0,0 +1,83 @@
+{
+    "type": "vla0",
+    "n_obs_steps": 1,
+    "input_features": {
+        "observation.images.image": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                256,
+                256
+            ]
+        },
+        "observation.images.image2": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                256,
+                256
+            ]
+        },
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                8
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                7
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": true,
+    "amp_dtype": "bf16",
+    "push_to_hub": true,
+    "repo_id": "olegbalakhnov/libero_vla0_final",
+    "private": null,
+    "tags": null,
+    "license": null,
+    "pretrained_path": null,
+    "chunk_size": 8,
+    "n_action_steps": 8,
+    "ensemble_size": 0,
+    "normalization_mapping": {
+        "VISUAL": "IDENTITY",
+        "STATE": "MIN_MAX",
+        "ACTION": "MIN_MAX"
+    },
+    "n_action_bins": 512,
+    "n_state_bins": 512,
+    "max_decoding_steps": 512,
+    "use_cache": true,
+    "optimizer_lr": 5e-05,
+    "optimizer_betas": [
+        0.9,
+        0.95
+    ],
+    "optimizer_eps": 1e-08,
+    "optimizer_weight_decay": 0.01,
+    "scheduler_warmup_steps": 1000,
+    "scheduler_decay_steps": 100000,
+    "scheduler_decay_lr": 5e-06,
+    "checkpoint_path": null,
+    "vlm_checkpoint": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
+    "precision": "float32",
+    "freeze_vision_encoder": false,
+    "do_image_splitting": false,
+    "drop_n_last_frames": 1,
+    "relative_actions": false,
+    "use_state": true,
+    "start_actions_token": 49279,
+    "grad_clip_norm": 1.0,
+    "action_mask_aug_per": 0.15,
+    "action_mask_skip_per": 0.1,
+    "crop_shape": [
+        230,
+        230
+    ]
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c9b0a0db020cfbbccf06a761c864a860f90bbc0d43a2f5a19cdda2a1bb3ff4d
+size 2030003168

train_config.json

@@ -0,0 +1,213 @@
+{
+    "dataset": {
+        "repo_id": "HuggingFaceVLA/libero",
+        "root": null,
+        "episodes": null,
+        "image_transforms": {
+            "enable": false,
+            "max_num_transforms": 3,
+            "random_order": false,
+            "tfs": {
+                "brightness": {
+                    "weight": 1.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "brightness": [
+                            0.8,
+                            1.2
+                        ]
+                    }
+                },
+                "contrast": {
+                    "weight": 1.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "contrast": [
+                            0.8,
+                            1.2
+                        ]
+                    }
+                },
+                "saturation": {
+                    "weight": 1.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "saturation": [
+                            0.5,
+                            1.5
+                        ]
+                    }
+                },
+                "hue": {
+                    "weight": 1.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "hue": [
+                            -0.05,
+                            0.05
+                        ]
+                    }
+                },
+                "sharpness": {
+                    "weight": 1.0,
+                    "type": "SharpnessJitter",
+                    "kwargs": {
+                        "sharpness": [
+                            0.5,
+                            1.5
+                        ]
+                    }
+                },
+                "affine": {
+                    "weight": 1.0,
+                    "type": "RandomAffine",
+                    "kwargs": {
+                        "degrees": [
+                            -5.0,
+                            5.0
+                        ],
+                        "translate": [
+                            0.05,
+                            0.05
+                        ]
+                    }
+                }
+            }
+        },
+        "revision": null,
+        "use_imagenet_stats": true,
+        "video_backend": "torchcodec",
+        "streaming": false
+    },
+    "env": null,
+    "policy": {
+        "type": "vla0",
+        "n_obs_steps": 1,
+        "input_features": {
+            "observation.images.image": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    256,
+                    256
+                ]
+            },
+            "observation.images.image2": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    256,
+                    256
+                ]
+            },
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    8
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    7
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": true,
+        "amp_dtype": "bf16",
+        "push_to_hub": true,
+        "repo_id": "olegbalakhnov/libero_vla0_final",
+        "private": null,
+        "tags": null,
+        "license": null,
+        "pretrained_path": null,
+        "chunk_size": 8,
+        "n_action_steps": 8,
+        "ensemble_size": 0,
+        "normalization_mapping": {
+            "VISUAL": "IDENTITY",
+            "STATE": "MIN_MAX",
+            "ACTION": "MIN_MAX"
+        },
+        "n_action_bins": 512,
+        "n_state_bins": 512,
+        "max_decoding_steps": 512,
+        "use_cache": true,
+        "optimizer_lr": 5e-05,
+        "optimizer_betas": [
+            0.9,
+            0.95
+        ],
+        "optimizer_eps": 1e-08,
+        "optimizer_weight_decay": 0.01,
+        "scheduler_warmup_steps": 1000,
+        "scheduler_decay_steps": 100000,
+        "scheduler_decay_lr": 5e-06,
+        "checkpoint_path": null,
+        "vlm_checkpoint": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
+        "precision": "float32",
+        "freeze_vision_encoder": false,
+        "do_image_splitting": false,
+        "drop_n_last_frames": 1,
+        "relative_actions": false,
+        "use_state": true,
+        "start_actions_token": 49279,
+        "grad_clip_norm": 1.0,
+        "action_mask_aug_per": 0.15,
+        "action_mask_skip_per": 0.1,
+        "crop_shape": [
+            230,
+            230
+        ]
+    },
+    "output_dir": "outputs/train/2025-12-09/23-23-58_vla0",
+    "job_name": "vla0",
+    "resume": false,
+    "seed": 1000,
+    "num_workers": 8,
+    "batch_size": 24,
+    "steps": 100000,
+    "eval_freq": 25000,
+    "log_freq": 200,
+    "save_checkpoint": true,
+    "save_freq": 25000,
+    "profile_step_num": -1,
+    "use_policy_training_preset": true,
+    "optimizer": {
+        "type": "adamw",
+        "lr": 5e-05,
+        "weight_decay": 0.01,
+        "grad_clip_norm": 1.0,
+        "betas": [
+            0.9,
+            0.95
+        ],
+        "eps": 1e-08
+    },
+    "scheduler": {
+        "type": "cosine_decay_with_warmup",
+        "num_warmup_steps": 1000,
+        "num_decay_steps": 100000,
+        "peak_lr": 5e-05,
+        "decay_lr": 5e-06
+    },
+    "eval": {
+        "n_episodes": 4,
+        "batch_size": 4,
+        "use_async_envs": false
+    },
+    "wandb": {
+        "enable": true,
+        "disable_artifact": false,
+        "project": "lerobot",
+        "entity": null,
+        "notes": null,
+        "run_id": "wix4h6e7",
+        "mode": null
+    },
+    "checkpoint_path": null,
+    "rename_map": {}
+}