Upload policy weights, train config and readme

README.md

@@ -0,0 +1,62 @@
+---
+datasets: imstevenpmwork/super_chatton
+library_name: lerobot
+license: apache-2.0
+model_name: evo1
+pipeline_tag: robotics
+tags:
+- robotics
+- evo1
+- lerobot
+---
+
+# Model Card for evo1
+
+<!-- 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 +1,101 @@
+{
+    "type": "evo1",
+    "n_obs_steps": 1,
+    "input_features": {
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                6
+            ]
+        },
+        "observation.images.front": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                480,
+                640
+            ]
+        },
+        "observation.images.wrist": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                480,
+                640
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                6
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": true,
+    "use_peft": false,
+    "push_to_hub": true,
+    "repo_id": "imstevenpmwork/super_chatton_evo2",
+    "private": null,
+    "tags": null,
+    "license": null,
+    "pretrained_path": null,
+    "training_stage": "stage2",
+    "chunk_size": 50,
+    "n_action_steps": 50,
+    "max_state_dim": 6,
+    "max_action_dim": 6,
+    "max_views": 3,
+    "image_resolution": [
+        448,
+        448
+    ],
+    "empty_cameras": 0,
+    "postprocess_action_dim": null,
+    "binarize_gripper": false,
+    "gripper_index": 6,
+    "gripper_threshold": 0.5,
+    "gripper_below_threshold_value": 1.0,
+    "gripper_above_threshold_value": -1.0,
+    "normalization_mapping": {
+        "VISUAL": "IDENTITY",
+        "STATE": "MIN_MAX",
+        "ACTION": "MIN_MAX"
+    },
+    "vlm_model_name": "OpenGVLab/InternVL3-1B-hf",
+    "vlm_num_layers": 14,
+    "vlm_dtype": "bfloat16",
+    "use_flash_attn": true,
+    "action_head": "flowmatching",
+    "embed_dim": 896,
+    "hidden_dim": 1024,
+    "state_hidden_dim": 1024,
+    "num_heads": 8,
+    "num_layers": 8,
+    "dropout": 0.0,
+    "num_inference_timesteps": 32,
+    "num_categories": 1,
+    "return_cls_only": false,
+    "enable_gradient_checkpointing": true,
+    "gradient_checkpointing_use_reentrant": false,
+    "finetune_vlm": true,
+    "finetune_language_model": true,
+    "finetune_vision_model": true,
+    "finetune_action_head": true,
+    "apply_training_stage_defaults": true,
+    "task_field": "task",
+    "embodiment_id_field": null,
+    "default_embodiment_id": 0,
+    "optimizer_lr": 0.0001,
+    "optimizer_betas": [
+        0.9,
+        0.999
+    ],
+    "optimizer_eps": 1e-08,
+    "optimizer_weight_decay": 1e-05,
+    "optimizer_grad_clip_norm": 1.0,
+    "scheduler_warmup_steps": 1000,
+    "drop_last": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f95c26cf6b776e9dbdacc42dfb2f8ed9257f94e6d811b99e44e060335a5d6b3
+size 1794493536

train_config.json

@@ -0,0 +1,236 @@
+{
+    "dataset": {
+        "repo_id": "imstevenpmwork/super_chatton",
+        "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": false,
+        "video_backend": "torchcodec",
+        "return_uint8": false,
+        "streaming": false
+    },
+    "env": null,
+    "policy": {
+        "type": "evo1",
+        "n_obs_steps": 1,
+        "input_features": {
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    6
+                ]
+            },
+            "observation.images.front": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    480,
+                    640
+                ]
+            },
+            "observation.images.wrist": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    480,
+                    640
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    6
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": true,
+        "use_peft": false,
+        "push_to_hub": true,
+        "repo_id": "imstevenpmwork/super_chatton_evo2",
+        "private": null,
+        "tags": null,
+        "license": null,
+        "pretrained_path": null,
+        "training_stage": "stage2",
+        "chunk_size": 50,
+        "n_action_steps": 50,
+        "max_state_dim": 6,
+        "max_action_dim": 6,
+        "max_views": 3,
+        "image_resolution": [
+            448,
+            448
+        ],
+        "empty_cameras": 0,
+        "postprocess_action_dim": null,
+        "binarize_gripper": false,
+        "gripper_index": 6,
+        "gripper_threshold": 0.5,
+        "gripper_below_threshold_value": 1.0,
+        "gripper_above_threshold_value": -1.0,
+        "normalization_mapping": {
+            "VISUAL": "IDENTITY",
+            "STATE": "MIN_MAX",
+            "ACTION": "MIN_MAX"
+        },
+        "vlm_model_name": "OpenGVLab/InternVL3-1B-hf",
+        "vlm_num_layers": 14,
+        "vlm_dtype": "bfloat16",
+        "use_flash_attn": true,
+        "action_head": "flowmatching",
+        "embed_dim": 896,
+        "hidden_dim": 1024,
+        "state_hidden_dim": 1024,
+        "num_heads": 8,
+        "num_layers": 8,
+        "dropout": 0.0,
+        "num_inference_timesteps": 32,
+        "num_categories": 1,
+        "return_cls_only": false,
+        "enable_gradient_checkpointing": true,
+        "gradient_checkpointing_use_reentrant": false,
+        "finetune_vlm": true,
+        "finetune_language_model": true,
+        "finetune_vision_model": true,
+        "finetune_action_head": true,
+        "apply_training_stage_defaults": true,
+        "task_field": "task",
+        "embodiment_id_field": null,
+        "default_embodiment_id": 0,
+        "optimizer_lr": 0.0001,
+        "optimizer_betas": [
+            0.9,
+            0.999
+        ],
+        "optimizer_eps": 1e-08,
+        "optimizer_weight_decay": 1e-05,
+        "optimizer_grad_clip_norm": 1.0,
+        "scheduler_warmup_steps": 1000,
+        "drop_last": true
+    },
+    "reward_model": null,
+    "output_dir": "outputs/train/2026-07-01/22-47-07_evo1",
+    "job_name": "evo1",
+    "resume": false,
+    "seed": 1000,
+    "cudnn_deterministic": false,
+    "num_workers": 4,
+    "batch_size": 32,
+    "prefetch_factor": 4,
+    "persistent_workers": true,
+    "steps": 8000,
+    "eval_freq": 20000,
+    "log_freq": 80,
+    "tolerance_s": 0.0001,
+    "save_checkpoint": true,
+    "save_freq": 4000,
+    "use_policy_training_preset": true,
+    "optimizer": {
+        "type": "adamw",
+        "lr": 0.0001,
+        "weight_decay": 1e-05,
+        "grad_clip_norm": 1.0,
+        "betas": [
+            0.9,
+            0.999
+        ],
+        "eps": 1e-08
+    },
+    "scheduler": {
+        "type": "evo1_exact",
+        "num_warmup_steps": 1000
+    },
+    "eval": {
+        "n_episodes": 50,
+        "batch_size": 50,
+        "use_async_envs": true
+    },
+    "wandb": {
+        "enable": true,
+        "disable_artifact": true,
+        "project": "lerobot",
+        "entity": null,
+        "notes": null,
+        "run_id": "nmquirjw",
+        "mode": null,
+        "add_tags": true
+    },
+    "peft": null,
+    "sample_weighting": null,
+    "rename_map": {},
+    "checkpoint_path": null
+}