Upload policy weights, train config and readme

README.md

@@ -0,0 +1,62 @@
+---
+datasets: globcy/libero_dir_trace_90
+library_name: lerobot
+license: apache-2.0
+model_name: openvla
+pipeline_tag: robotics
+tags:
+- openvla
+- robotics
+- lerobot
+---
+
+# Model Card for openvla
+
+<!-- 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

adapter_config.json

@@ -0,0 +1,60 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "OpenVLAPolicy",
+    "parent_library": "lerobot.policies.openvla.modeling_openvla"
+  },
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [],
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "attn.proj",
+    "q",
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "fc2",
+    "up_proj",
+    "projector.0",
+    "projector.4",
+    "attn_pool.proj",
+    "projector.2",
+    "fc1",
+    "lm_head",
+    "kv",
+    "down_proj",
+    "qkv",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9faebdb716a6a8c40ec031d648cfb7ab78f5a40be0dfccd0da3147611f1e981
+size 221580936

config.json

@@ -0,0 +1,67 @@
+{
+    "type": "openvla",
+    "n_obs_steps": 1,
+    "input_features": {
+        "observation.images.image": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                224,
+                224
+            ]
+        },
+        "observation.images.image2": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                224,
+                224
+            ]
+        },
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                8
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                7
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": false,
+    "use_peft": true,
+    "push_to_hub": true,
+    "repo_id": "globcy/openvla_high_level_dir_only_90_bottom_up",
+    "private": null,
+    "tags": null,
+    "license": null,
+    "pretrained_path": null,
+    "pretrained_checkpoint": "/pfss/mlde/workspaces/mlde_wsp_Rohrbach/users/cb14syta/Embodied-CoT/steerable-policy-embodied-reasoner-7b",
+    "text_tokenizer_name": "meta-llama/Llama-2-7b-hf",
+    "tokenizer_max_length": 2048,
+    "dtype": "bfloat16",
+    "reason": false,
+    "chunk_size": 25,
+    "image_resolution": [
+        224,
+        224
+    ],
+    "hierarchical": true,
+    "dynamic_action_chunking": "move",
+    "gradient_checkpointing": true,
+    "compile_model": false,
+    "normalization_mapping": {
+        "VISUAL": "IDENTITY",
+        "STATE": "MEAN_STD",
+        "ACTION": "MEAN_STD"
+    },
+    "optimizer_lr": 0.00025,
+    "optimizer_weight_decay": 0.0,
+    "optimizer_grad_clip_norm": 1.0
+}

train_config.json

@@ -0,0 +1,215 @@
+{
+    "dataset": {
+        "repo_id": "globcy/libero_dir_trace_90",
+        "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",
+        "return_uint8": false,
+        "streaming": false
+    },
+    "env": null,
+    "policy": {
+        "type": "openvla",
+        "n_obs_steps": 1,
+        "input_features": {
+            "observation.images.image": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    224,
+                    224
+                ]
+            },
+            "observation.images.image2": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    224,
+                    224
+                ]
+            },
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    8
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    7
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": false,
+        "use_peft": true,
+        "push_to_hub": true,
+        "repo_id": "globcy/openvla_high_level_dir_only_90_bottom_up",
+        "private": null,
+        "tags": null,
+        "license": null,
+        "pretrained_path": null,
+        "pretrained_checkpoint": "/pfss/mlde/workspaces/mlde_wsp_Rohrbach/users/cb14syta/Embodied-CoT/steerable-policy-embodied-reasoner-7b",
+        "text_tokenizer_name": "meta-llama/Llama-2-7b-hf",
+        "tokenizer_max_length": 2048,
+        "dtype": "bfloat16",
+        "reason": false,
+        "chunk_size": 25,
+        "image_resolution": [
+            224,
+            224
+        ],
+        "hierarchical": true,
+        "dynamic_action_chunking": "move",
+        "gradient_checkpointing": true,
+        "compile_model": false,
+        "normalization_mapping": {
+            "VISUAL": "IDENTITY",
+            "STATE": "MEAN_STD",
+            "ACTION": "MEAN_STD"
+        },
+        "optimizer_lr": 0.00025,
+        "optimizer_weight_decay": 0.0,
+        "optimizer_grad_clip_norm": 1.0
+    },
+    "output_dir": "outputs/openvla_high_level_dir_only_90_bottom_up",
+    "job_name": "openvla_high_level_dir_only_90_bottom_up",
+    "resume": false,
+    "seed": 1000,
+    "cudnn_deterministic": false,
+    "num_workers": 4,
+    "batch_size": 16,
+    "prefetch_factor": 4,
+    "persistent_workers": true,
+    "steps": 30000,
+    "eval_freq": 20000,
+    "log_freq": 200,
+    "tolerance_s": 0.0001,
+    "save_checkpoint": true,
+    "save_freq": 10000,
+    "use_policy_training_preset": true,
+    "optimizer": {
+        "type": "adamw",
+        "lr": 0.00025,
+        "weight_decay": 0.0,
+        "grad_clip_norm": 10.0,
+        "betas": [
+            0.9,
+            0.999
+        ],
+        "eps": 1e-08
+    },
+    "scheduler": null,
+    "eval": {
+        "n_episodes": 50,
+        "batch_size": 22,
+        "use_async_envs": true
+    },
+    "wandb": {
+        "enable": false,
+        "disable_artifact": false,
+        "project": "lerobot",
+        "entity": null,
+        "notes": null,
+        "run_id": null,
+        "mode": null,
+        "add_tags": true
+    },
+    "peft": {
+        "target_modules": null,
+        "full_training_modules": null,
+        "method_type": "LORA",
+        "init_type": null,
+        "r": 16,
+        "lora_alpha": 32,
+        "lora_dropout": 0.1
+    },
+    "use_rabc": false,
+    "rabc_progress_path": null,
+    "rabc_kappa": 0.01,
+    "rabc_epsilon": 1e-06,
+    "rabc_head_mode": "sparse",
+    "rename_map": {},
+    "checkpoint_path": null,
+    "bottom_up": true,
+    "bottom_up_chunk_size": 25,
+    "reader_chain_close": 0,
+    "reader_chain_dir": false,
+    "is_planner": true
+}