Upload policy weights, train config and readme

README.md

@@ -0,0 +1,62 @@
+---
+datasets: antwoor/collect_with_dif_tsks_degrees
+library_name: lerobot
+license: apache-2.0
+model_name: pi0fast
+pipeline_tag: robotics
+tags:
+- lerobot
+- pi0fast
+- robotics
+---
+
+# Model Card for pi0fast
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+[Pi0-Fast](https://huggingface.co/papers/2501.09747) is a variant of Pi0 that uses a new tokenization method called FAST, which enables training of an autoregressive vision-language-action policy for high-frequency robotic tasks with improved performance and reduced training time.
+
+
+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": "pi0fast",
+    "n_obs_steps": 1,
+    "normalization_mapping": {
+        "VISUAL": "IDENTITY",
+        "STATE": "MEAN_STD",
+        "ACTION": "MEAN_STD"
+    },
+    "input_features": {
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                7
+            ]
+        },
+        "observation.images.camera_1": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                480,
+                640
+            ]
+        },
+        "observation.images.camera_2": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                480,
+                640
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                7
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": false,
+    "push_to_hub": true,
+    "repo_id": "antwoor/based_pi0_diff",
+    "private": null,
+    "tags": null,
+    "license": null,
+    "chunk_size": 10,
+    "n_action_steps": 5,
+    "max_state_dim": 32,
+    "max_action_dim": 32,
+    "resize_imgs_with_padding": [
+        224,
+        224
+    ],
+    "interpolate_like_pi": false,
+    "empty_cameras": 0,
+    "adapt_to_pi_aloha": false,
+    "use_delta_joint_actions_aloha": false,
+    "tokenizer_max_length": 48,
+    "proj_width": 1024,
+    "max_decoding_steps": 256,
+    "fast_skip_tokens": 128,
+    "max_input_seq_len": 256,
+    "use_cache": true,
+    "freeze_vision_encoder": true,
+    "freeze_lm_head": true,
+    "optimizer_lr": 0.0001,
+    "optimizer_betas": [
+        0.9,
+        0.95
+    ],
+    "optimizer_eps": 1e-08,
+    "optimizer_weight_decay": 1e-05,
+    "scheduler_warmup_steps": 1000,
+    "scheduler_decay_steps": 30000,
+    "scheduler_decay_lr": 2.5e-06,
+    "checkpoint_path": null,
+    "padding_side": "right",
+    "precision": "bfloat16",
+    "grad_clip_norm": 1,
+    "relaxed_action_decoding": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b387c535a79f85cb78fe70627e0759520a09f3d45d7d1b89b8491e36cd1889a0
+size 5846765784

train_config.json

@@ -0,0 +1,268 @@
+{
+    "dataset": {
+        "repo_id": "antwoor/collect_with_dif_tsks_degrees",
+        "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
+                        ]
+                    }
+                }
+            }
+        },
+        "revision": null,
+        "use_imagenet_stats": true,
+        "video_backend": "torchcodec"
+    },
+    "env": {
+        "type": "mcx",
+        "task": "pick all objects and place it in the box",
+        "fps": 30,
+        "features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    7
+                ]
+            },
+            "pixels": {
+                "type": "VISUAL",
+                "shape": [
+                    480,
+                    640,
+                    3
+                ]
+            },
+            "agent_pos": {
+                "type": "STATE",
+                "shape": [
+                    7
+                ]
+            }
+        },
+        "features_map": {
+            "action": "action",
+            "agent_pos": "observation.state",
+            "pixels": "observation.image"
+        },
+        "ip": "192.168.56.101",
+        "obs_type": "pixels_agent_pos",
+        "action_mean": [
+            0.0,
+            0.0,
+            0.0,
+            0.0,
+            0.0,
+            0.0,
+            0.0
+        ],
+        "action_std": [
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0
+        ],
+        "agent_pos_mean": [
+            0.0,
+            0.0,
+            0.0,
+            0.0,
+            0.0,
+            0.0,
+            0.0
+        ],
+        "agent_pos_std": [
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0
+        ],
+        "episode_length": 30,
+        "render_mode": "rgb_array",
+        "visualization_width": 480,
+        "visualization_height": 640
+    },
+    "policy": {
+        "type": "pi0fast",
+        "n_obs_steps": 1,
+        "normalization_mapping": {
+            "VISUAL": "IDENTITY",
+            "STATE": "MEAN_STD",
+            "ACTION": "MEAN_STD"
+        },
+        "input_features": {
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    7
+                ]
+            },
+            "observation.images.camera_1": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    480,
+                    640
+                ]
+            },
+            "observation.images.camera_2": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    480,
+                    640
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    7
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": false,
+        "push_to_hub": true,
+        "repo_id": "antwoor/based_pi0_diff",
+        "private": null,
+        "tags": null,
+        "license": null,
+        "chunk_size": 10,
+        "n_action_steps": 5,
+        "max_state_dim": 32,
+        "max_action_dim": 32,
+        "resize_imgs_with_padding": [
+            224,
+            224
+        ],
+        "interpolate_like_pi": false,
+        "empty_cameras": 0,
+        "adapt_to_pi_aloha": false,
+        "use_delta_joint_actions_aloha": false,
+        "tokenizer_max_length": 48,
+        "proj_width": 1024,
+        "max_decoding_steps": 256,
+        "fast_skip_tokens": 128,
+        "max_input_seq_len": 256,
+        "use_cache": true,
+        "freeze_vision_encoder": true,
+        "freeze_lm_head": true,
+        "optimizer_lr": 0.0001,
+        "optimizer_betas": [
+            0.9,
+            0.95
+        ],
+        "optimizer_eps": 1e-08,
+        "optimizer_weight_decay": 1e-05,
+        "scheduler_warmup_steps": 1000,
+        "scheduler_decay_steps": 30000,
+        "scheduler_decay_lr": 2.5e-06,
+        "checkpoint_path": null,
+        "padding_side": "right",
+        "precision": "bfloat16",
+        "grad_clip_norm": 1,
+        "relaxed_action_decoding": true
+    },
+    "output_dir": "outputs/train/2025-10-07/21-36-43_mcx_pi0fast",
+    "job_name": "mcx_pi0fast",
+    "resume": false,
+    "seed": 1000,
+    "num_workers": 4,
+    "batch_size": 8,
+    "steps": 1000,
+    "eval_freq": -1,
+    "log_freq": 25,
+    "save_checkpoint": true,
+    "save_freq": 20000,
+    "use_policy_training_preset": true,
+    "optimizer": {
+        "type": "adamw",
+        "lr": 0.0001,
+        "weight_decay": 1e-05,
+        "grad_clip_norm": 1,
+        "betas": [
+            0.9,
+            0.95
+        ],
+        "eps": 1e-08
+    },
+    "scheduler": {
+        "type": "cosine_decay_with_warmup",
+        "num_warmup_steps": 1000,
+        "num_decay_steps": 30000,
+        "peak_lr": 0.0001,
+        "decay_lr": 2.5e-06
+    },
+    "eval": {
+        "n_episodes": 50,
+        "batch_size": 50,
+        "use_async_envs": false
+    },
+    "wandb": {
+        "enable": false,
+        "disable_artifact": false,
+        "project": "lerobot",
+        "entity": null,
+        "notes": null,
+        "run_id": null,
+        "mode": null
+    }
+}