Upload folder using huggingface_hub

config.json

@@ -0,0 +1,108 @@
+{
+    "type": "pi05",
+    "n_obs_steps": 1,
+    "input_features": {
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                32
+            ]
+        },
+        "observation.state_eepose": {
+            "type": "STATE",
+            "shape": [
+                14
+            ]
+        },
+        "observation.images.cam_high": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                360,
+                480
+            ]
+        },
+        "observation.images.cam_left_wrist": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                360,
+                480
+            ]
+        },
+        "observation.images.cam_right_wrist": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                360,
+                480
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                32
+            ]
+        },
+        "action_eepose": {
+            "type": "ACTION",
+            "shape": [
+                14
+            ]
+        }
+    },
+    "device": "cpu",
+    "use_amp": false,
+    "push_to_hub": false,
+    "repo_id": null,
+    "private": null,
+    "tags": null,
+    "license": null,
+    "pretrained_path": "checkpoints/pi05_base",
+    "paligemma_variant": "gemma_2b",
+    "action_expert_variant": "gemma_300m",
+    "dtype": "bfloat16",
+    "chunk_size": 50,
+    "n_action_steps": 50,
+    "max_state_dim": 32,
+    "max_action_dim": 32,
+    "state_cond": true,
+    "num_inference_steps": 10,
+    "time_sampling_beta_alpha": 1.5,
+    "time_sampling_beta_beta": 1.0,
+    "time_sampling_scale": 0.999,
+    "time_sampling_offset": 0.001,
+    "min_period": 0.004,
+    "max_period": 4.0,
+    "image_resolution": [
+        224,
+        224
+    ],
+    "empty_cameras": 0,
+    "tokenizer_max_length": 200,
+    "normalization_mapping": {
+        "VISUAL": "IDENTITY",
+        "STATE": "MEAN_STD",
+        "ACTION": "MEAN_STD"
+    },
+    "gradient_checkpointing": false,
+    "compile_model": false,
+    "compile_mode": "max-autotune",
+    "fuse_qkv": false,
+    "fuse_gate_up": false,
+    "optimizer_lr": 2.5e-05,
+    "optimizer_betas": [
+        0.9,
+        0.95
+    ],
+    "optimizer_eps": 1e-08,
+    "optimizer_weight_decay": 0.01,
+    "optimizer_grad_clip_norm": 1.0,
+    "scheduler_warmup_steps": 1000,
+    "scheduler_decay_steps": 30000,
+    "scheduler_decay_lr": 2.5e-06,
+    "vlm_config": {},
+    "action_expert_config": {}
+}

lora_adapters/README.md

@@ -0,0 +1,203 @@
+---
+library_name: peft
+tags:
+- lora
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

lora_adapters/adapter_config.json

@@ -0,0 +1,131 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "action_expert.model.layers.16.input_layernorm.dense",
+    "vlm.model.language_model.layers.13.input_layernorm",
+    "action_expert.model.layers.17.post_attention_layernorm.dense",
+    "action_expert.model.layers.6.input_layernorm.dense",
+    "action_expert.model.layers.5.post_attention_layernorm.dense",
+    "action_expert.model.layers.13.input_layernorm.dense",
+    "vlm.model.language_model.layers.7.input_layernorm",
+    "vlm.model.language_model.layers.0.post_attention_layernorm",
+    "action_expert.model.layers.3.post_attention_layernorm.dense",
+    "vlm.model.language_model.layers.6.input_layernorm",
+    "action_expert.model.layers.7.post_attention_layernorm.dense",
+    "action_expert.model.layers.10.post_attention_layernorm.dense",
+    "action_expert.model.layers.5.input_layernorm.dense",
+    "vlm.model.language_model.layers.14.post_attention_layernorm",
+    "suffix_embedder.time_mlp_in",
+    "vlm.model.language_model.layers.11.post_attention_layernorm",
+    "vlm.model.language_model.layers.15.post_attention_layernorm",
+    "vlm.model.language_model.layers.17.input_layernorm",
+    "action_expert.model.layers.8.post_attention_layernorm.dense",
+    "action_expert.model.layers.1.post_attention_layernorm.dense",
+    "action_expert.model.layers.14.post_attention_layernorm.dense",
+    "action_out_proj",
+    "action_expert.model.layers.14.input_layernorm.dense",
+    "vlm.model.language_model.layers.2.post_attention_layernorm",
+    "vlm.model.language_model.layers.1.post_attention_layernorm",
+    "action_expert.model.layers.4.input_layernorm.dense",
+    "action_expert.model.layers.15.input_layernorm.dense",
+    "vlm.model.vision_tower.vision_model.embeddings.position_embedding",
+    "vlm.model.language_model.layers.15.input_layernorm",
+    "action_expert.model.layers.4.post_attention_layernorm.dense",
+    "vlm.model.language_model.layers.17.post_attention_layernorm",
+    "vlm.model.language_model.layers.0.input_layernorm",
+    "action_expert.model.layers.0.post_attention_layernorm.dense",
+    "vlm.model.language_model.layers.6.post_attention_layernorm",
+    "vlm.model.language_model.layers.4.input_layernorm",
+    "action_expert.model.layers.0.input_layernorm.dense",
+    "vlm.model.language_model.layers.3.post_attention_layernorm",
+    "vlm.model.language_model.layers.5.post_attention_layernorm",
+    "action_expert.model.layers.11.post_attention_layernorm.dense",
+    "vlm.model.language_model.layers.8.input_layernorm",
+    "vlm.model.language_model.layers.12.post_attention_layernorm",
+    "suffix_embedder.state_proj",
+    "action_expert.model.layers.12.input_layernorm.dense",
+    "vlm.model.language_model.layers.9.post_attention_layernorm",
+    "action_expert.model.layers.15.post_attention_layernorm.dense",
+    "action_expert.model.layers.8.input_layernorm.dense",
+    "vlm.model.language_model.layers.12.input_layernorm",
+    "action_expert.model.layers.16.post_attention_layernorm.dense",
+    "vlm.model.language_model.layers.4.post_attention_layernorm",
+    "suffix_embedder.state_mlp_out",
+    "vlm.model.language_model.layers.8.post_attention_layernorm",
+    "action_expert.model.layers.17.input_layernorm.dense",
+    "vlm.model.language_model.layers.10.input_layernorm",
+    "action_expert.model.layers.2.input_layernorm.dense",
+    "vlm.model.language_model.layers.11.input_layernorm",
+    "action_expert.model.layers.13.post_attention_layernorm.dense",
+    "vlm.model.language_model.layers.16.input_layernorm",
+    "action_expert.model.layers.1.input_layernorm.dense",
+    "action_expert.model.layers.9.input_layernorm.dense",
+    "vlm.model.language_model.layers.13.post_attention_layernorm",
+    "action_expert.model.layers.7.input_layernorm.dense",
+    "action_expert.model.layers.6.post_attention_layernorm.dense",
+    "vlm.model.language_model.layers.2.input_layernorm",
+    "vlm.model.language_model.layers.16.post_attention_layernorm",
+    "vlm.model.language_model.layers.14.input_layernorm",
+    "vlm.model.language_model.layers.10.post_attention_layernorm",
+    "suffix_embedder.action_in_proj",
+    "vlm.model.vision_tower.vision_model.embeddings.patch_embedding",
+    "vlm.model.language_model.layers.7.post_attention_layernorm",
+    "vlm.model.language_model.layers.9.input_layernorm",
+    "action_expert.model.layers.12.post_attention_layernorm.dense",
+    "action_expert.model.layers.9.post_attention_layernorm.dense",
+    "vlm.model.language_model.layers.5.input_layernorm",
+    "suffix_embedder.time_mlp_out",
+    "action_expert.model.layers.10.input_layernorm.dense",
+    "action_expert.model.layers.3.input_layernorm.dense",
+    "action_expert.model.layers.11.input_layernorm.dense",
+    "suffix_embedder.state_mlp_in",
+    "action_expert.model.layers.2.post_attention_layernorm.dense",
+    "vlm.model.language_model.layers.3.input_layernorm",
+    "vlm.model.language_model.layers.1.input_layernorm"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "fc1",
+    "o_proj",
+    "down_proj",
+    "out_proj",
+    "gate_proj",
+    "up_proj",
+    "k_proj",
+    "fc2"
+  ],
+  "target_parameters": null,
+  "task_type": "FEATURE_EXTRACTION",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

lora_adapters/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85261c03d43be91d17611d44d2257533f66c839cb1fe56fe934dbdf87d61b051
+size 598447496

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8620fa70729c19e25f64c09597297f0e9266ebb8735b295712e0f86403462ce
+size 7481487344

train_config.json

@@ -0,0 +1,274 @@
+{
+    "dataset": {
+        "repo_id": "data/pickup0102_310",
+        "root": "data/pickup0102_310",
+        "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": "pi05",
+        "n_obs_steps": 1,
+        "input_features": {
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    32
+                ]
+            },
+            "observation.state_eepose": {
+                "type": "STATE",
+                "shape": [
+                    14
+                ]
+            },
+            "observation.images.cam_high": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    360,
+                    480
+                ]
+            },
+            "observation.images.cam_left_wrist": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    360,
+                    480
+                ]
+            },
+            "observation.images.cam_right_wrist": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    360,
+                    480
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    32
+                ]
+            },
+            "action_eepose": {
+                "type": "ACTION",
+                "shape": [
+                    14
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": false,
+        "push_to_hub": false,
+        "repo_id": null,
+        "private": null,
+        "tags": null,
+        "license": null,
+        "pretrained_path": "checkpoints/pi05_base",
+        "paligemma_variant": "gemma_2b",
+        "action_expert_variant": "gemma_300m",
+        "dtype": "bfloat16",
+        "chunk_size": 50,
+        "n_action_steps": 50,
+        "max_state_dim": 32,
+        "max_action_dim": 32,
+        "state_cond": true,
+        "num_inference_steps": 10,
+        "time_sampling_beta_alpha": 1.5,
+        "time_sampling_beta_beta": 1.0,
+        "time_sampling_scale": 0.999,
+        "time_sampling_offset": 0.001,
+        "min_period": 0.004,
+        "max_period": 4.0,
+        "image_resolution": [
+            224,
+            224
+        ],
+        "empty_cameras": 0,
+        "tokenizer_max_length": 200,
+        "normalization_mapping": {
+            "VISUAL": "IDENTITY",
+            "STATE": "MEAN_STD",
+            "ACTION": "MEAN_STD"
+        },
+        "gradient_checkpointing": false,
+        "compile_model": false,
+        "compile_mode": "max-autotune",
+        "fuse_qkv": false,
+        "fuse_gate_up": false,
+        "optimizer_lr": 2.5e-05,
+        "optimizer_betas": [
+            0.9,
+            0.95
+        ],
+        "optimizer_eps": 1e-08,
+        "optimizer_weight_decay": 0.01,
+        "optimizer_grad_clip_norm": 1.0,
+        "scheduler_warmup_steps": 1000,
+        "scheduler_decay_steps": 30000,
+        "scheduler_decay_lr": 2.5e-06,
+        "vlm_config": {},
+        "action_expert_config": {}
+    },
+    "output_dir": "outputs/train/pi05_async_lora",
+    "job_name": "pi05_async_lora",
+    "resume": false,
+    "seed": 1000,
+    "num_workers": 1,
+    "batch_size": 2,
+    "steps": 50000,
+    "eval_freq": 20000,
+    "log_freq": 50,
+    "save_checkpoint": true,
+    "save_freq": 10000,
+    "use_policy_training_preset": false,
+    "optimizer": {
+        "type": "adamw",
+        "lr": 0.0001,
+        "weight_decay": 1e-10,
+        "grad_clip_norm": 10.0,
+        "betas": [
+            0.9,
+            0.95
+        ],
+        "eps": 1e-08
+    },
+    "scheduler": {
+        "type": "cosine_decay_with_warmup",
+        "num_warmup_steps": 1000,
+        "num_decay_steps": 50000,
+        "peak_lr": 5e-05,
+        "decay_lr": 2.5e-06
+    },
+    "eval": {
+        "n_episodes": 50,
+        "batch_size": 50,
+        "use_async_envs": false
+    },
+    "wandb": {
+        "enable": false,
+        "disable_artifact": true,
+        "project": "vlash",
+        "entity": null,
+        "notes": null,
+        "run_id": null,
+        "mode": null
+    },
+    "checkpoint_path": null,
+    "rename_map": {},
+    "max_delay_steps": 8,
+    "grad_accum_steps": 8,
+    "shared_observation": false,
+    "lora": {
+        "enable": true,
+        "backend": "peft",
+        "r": 16,
+        "alpha": 16,
+        "dropout": 0.0,
+        "extra_trainable_modules": [
+            "action_in_proj",
+            "action_out_proj",
+            "time_mlp_in",
+            "time_mlp_out",
+            "state_proj",
+            "state_mlp_in",
+            "state_mlp_out",
+            "embeddings",
+            "input_layernorm",
+            "post_attention_layernorm"
+        ],
+        "target_modules": [
+            "q_proj",
+            "k_proj",
+            "v_proj",
+            "o_proj",
+            "gate_proj",
+            "up_proj",
+            "down_proj",
+            "out_proj",
+            "fc1",
+            "fc2"
+        ],
+        "use_qlora": false,
+        "qlora_quant_type": "nf4",
+        "qlora_compute_dtype": "bfloat16"
+    }
+}