Back up exact final dependency: xvla_libero

xvla_libero/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

xvla_libero/BACKUP_PROVENANCE.json

@@ -0,0 +1,111 @@
+{
+  "source_repo": "lerobot/xvla-libero",
+  "source_revision": "12e8783e996944f5c97e490d37d4c145484ed70a",
+  "method": "server-side copy after fresh on-server file hashing",
+  "verified_source_files": [
+    {
+      "path": "xvla_libero/.gitattributes",
+      "bytes": 1519,
+      "sha256": "11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361",
+      "source_repo": "lerobot/xvla-libero",
+      "source_revision": "12e8783e996944f5c97e490d37d4c145484ed70a"
+    },
+    {
+      "path": "xvla_libero/README.md",
+      "bytes": 3951,
+      "sha256": "236c6b453d8c54c12ab3ae1ed7dfe4bec98b0e69891b36e120cf3084d9b31fda",
+      "source_repo": "lerobot/xvla-libero",
+      "source_revision": "12e8783e996944f5c97e490d37d4c145484ed70a"
+    },
+    {
+      "path": "xvla_libero/config.json",
+      "bytes": 9307,
+      "sha256": "db9ff1de61760910dcc5d355528346144d6a80687212c8600cf31207f0f5e010",
+      "source_repo": "lerobot/xvla-libero",
+      "source_revision": "12e8783e996944f5c97e490d37d4c145484ed70a"
+    },
+    {
+      "path": "xvla_libero/model.safetensors",
+      "bytes": 3519073692,
+      "sha256": "2a0e29448111df56b9485cb1f964db799205794c49baeda48ef960589ce649ab",
+      "source_repo": "lerobot/xvla-libero",
+      "source_revision": "12e8783e996944f5c97e490d37d4c145484ed70a"
+    },
+    {
+      "path": "xvla_libero/policy_postprocessor.json",
+      "bytes": 575,
+      "sha256": "d1d73a18f14aca0e9db7cdbb3eb536adadf4960947347cb1645c9a246ea0acb4",
+      "source_repo": "lerobot/xvla-libero",
+      "source_revision": "12e8783e996944f5c97e490d37d4c145484ed70a"
+    },
+    {
+      "path": "xvla_libero/policy_preprocessor.json",
+      "bytes": 1635,
+      "sha256": "b416b9d27ff58eada06d0d01d92291aa09161ba7eff5b84279e50f4a647cd37d",
+      "source_repo": "lerobot/xvla-libero",
+      "source_revision": "12e8783e996944f5c97e490d37d4c145484ed70a"
+    }
+  ],
+  "historical_provenance": {
+    "model": "xvla_libero",
+    "manifest_sha256": "63f49030df571872ea781edc9c55325324f2e62bcd74ce251af92e669918d23d",
+    "source": "huggingface_official_metadata_mirror_payload",
+    "repo": "lerobot/xvla-libero",
+    "revision": "12e8783e996944f5c97e490d37d4c145484ed70a",
+    "files_total": 6,
+    "files_complete": 6,
+    "state": "complete",
+    "started_unix": 1790349929.1644478,
+    "files": [
+      {
+        "path": ".gitattributes",
+        "size": 1519,
+        "generation": null,
+        "sha256": null,
+        "md5_base64": null,
+        "git_blob_sha1": "a6344aac8c09253b3b630fb776ae94478aa0275b"
+      },
+      {
+        "path": "README.md",
+        "size": 3951,
+        "generation": null,
+        "sha256": null,
+        "md5_base64": null,
+        "git_blob_sha1": "6201d03949f13e29b13e89a50c1bc5ba70c4b17f"
+      },
+      {
+        "path": "config.json",
+        "size": 9307,
+        "generation": null,
+        "sha256": null,
+        "md5_base64": null,
+        "git_blob_sha1": "e0adaf281e0ff3ec92b9dce300266485101f08b3"
+      },
+      {
+        "path": "model.safetensors",
+        "size": 3519073692,
+        "generation": null,
+        "sha256": "2a0e29448111df56b9485cb1f964db799205794c49baeda48ef960589ce649ab",
+        "md5_base64": null,
+        "git_blob_sha1": null
+      },
+      {
+        "path": "policy_postprocessor.json",
+        "size": 575,
+        "generation": null,
+        "sha256": null,
+        "md5_base64": null,
+        "git_blob_sha1": "9eac32b83fe981091f302bc7f03ba863e163390d"
+      },
+      {
+        "path": "policy_preprocessor.json",
+        "size": 1635,
+        "generation": null,
+        "sha256": null,
+        "md5_base64": null,
+        "git_blob_sha1": "1d0a0fd8b6382b6930c91219e1a21afe65b7889a"
+      }
+    ],
+    "ended_unix": 1790351134.0775633
+  }
+}

xvla_libero/README.md

@@ -0,0 +1,143 @@
+---
+language:
+- en
+library_name: lerobot
+pipeline_tag: robotics
+tags:
+- vision-language-action
+- imitation-learning
+- lerobot
+inference: false
+license: apache-2.0
+datasets:
+- HuggingFaceVLA/libero
+---
+
+# X-VLA (LeRobot)
+
+X-VLA is a Vision-Language-Action foundation model that uses soft prompts to handle cross-embodiment and cross-domain robot control within a unified Transformer architecture.
+
+Checkpoint trained and evaluated on LIBERO tasks.
+
+**Original paper:** [X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model](https://arxiv.org/abs/2510.10274)
+**Reference implementation:** https://github.com/2toinf/X-VLA  
+**LeRobot implementation:** Follows the original reference code for compatibility.
+
+
+## Model description
+
+- **Inputs:** images (multi-view), proprio/state, optional language instruction
+- **Outputs:** continuous actions
+- **Training objective:** flow matching
+- **Action representation:** continuous
+- **Intended use:** Base model to fine tune on your specific use case
+
+
+## Quick start (inference on a real batch)
+
+### Installation
+
+```bash
+pip install "lerobot[xvla]"
+```
+For full installation details (including optional video dependencies such as ffmpeg for torchcodec), see the official documentation: https://huggingface.co/docs/lerobot/installation
+
+### Load model + dataset, run `select_action`
+
+```python
+import torch
+from lerobot.datasets.lerobot_dataset import LeRobotDataset
+from lerobot.policies.factory import make_pre_post_processors
+
+# Swap this import per-policy
+from lerobot.policies.xvla.modeling_xvla import XVLAPolicy
+
+# load a policy
+model_id = "lerobot/xvla-libero"  # <- swap checkpoint
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+policy = XVLAPolicy.from_pretrained(model_id).to(device).eval()
+
+preprocess, postprocess = make_pre_post_processors(
+    policy.config,
+    model_id,
+    preprocessor_overrides={"device_processor": {"device": str(device)}},
+)
+# load a lerobotdataset (we will replace with a simpler dataset)
+dataset = LeRobotDataset("lerobot/libero")
+
+# pick an episode
+episode_index = 0
+
+# each episode corresponds to a contiguous range of frame indices
+from_idx = dataset.meta.episodes["dataset_from_index"][episode_index]
+to_idx   = dataset.meta.episodes["dataset_to_index"][episode_index]
+
+# get a single frame from that episode (e.g. the first frame)
+frame_index = from_idx
+frame = dict(dataset[frame_index])
+
+batch = preprocess(frame)
+with torch.inference_mode():
+    pred_action = policy.select_action(batch)
+    # use your policy postprocess, this post process the action
+    # for instance unnormalize the actions, detokenize it etc..
+    pred_action = postprocess(pred_action)
+```
+
+
+## Training step (loss + backward)
+
+If you’re training / fine-tuning, you typically call `forward(...)` to get a loss and then:
+
+```python
+policy.train()
+batch = dict(dataset[0])
+batch = preprocess(batch)
+
+loss, outputs = policy.forward(batch)
+loss.backward()
+
+```
+
+> Notes:
+> 
+> - Some policies expose `policy(**batch)` or return a dict; keep this snippet aligned with the policy API.
+> - Use your trainer script (`lerobot-train`) for full training loops.
+
+
+## How to train / fine-tune
+
+```bash
+lerobot-train \
+  --dataset.repo_id=${HF_USER}/<dataset> \
+  --output_dir=./outputs/[RUN_NAME] \
+  --job_name=[RUN_NAME] \
+  --policy.repo_id=${HF_USER}/<desired_policy_repo_id> \
+  --policy.path=lerobot/[BASE_CHECKPOINT] \
+  --policy.dtype=bfloat16 \
+  --policy.device=cuda \
+  --steps=100000 \
+  --batch_size=4
+```
+
+Add policy-specific flags below:
+
+- `-policy.chunk_size=...`
+- `-policy.n_action_steps=...`
+- `-policy.max_action_tokens=...`
+- `-policy.gradient_checkpointing=true`
+
+
+## Evaluate in Simulation (LIBERO)
+
+You can evaluate the model in Libero environment.
+
+```bash
+lerobot-eval \
+  --policy.path=lerobot/xvla-libero \
+  --env.type=libero \
+  --env.task=libero_object \
+  --eval.batch_size=1 \
+  --eval.n_episodes=20
+```

xvla_libero/config.json

@@ -0,0 +1,320 @@
+{
+    "type": "xvla",
+    "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
+            ]
+        },
+        "observation.images.empty_camera_0": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                224,
+                224
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                20
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": false,
+    "push_to_hub": true,
+    "repo_id": null,
+    "private": null,
+    "tags": null,
+    "license": null,
+    "pretrained_path": null,
+    "chunk_size": 30,
+    "n_action_steps": 30,
+    "normalization_mapping": {
+        "STATE": "IDENTITY",
+        "ACTION": "IDENTITY",
+        "VISUAL": "IDENTITY"
+    },
+    "florence_config": {
+        "_attn_implementation_autoset": true,
+        "bos_token_id": 0,
+        "eos_token_id": 2,
+        "ignore_index": -100,
+        "is_encoder_decoder": true,
+        "model_type": "florence2",
+        "pad_token_id": 1,
+        "projection_dim": 1024,
+        "text_config": {
+            "_attn_implementation_autoset": true,
+            "_name_or_path": "",
+            "activation_dropout": 0.1,
+            "activation_function": "gelu",
+            "add_cross_attention": false,
+            "architectures": null,
+            "attention_dropout": 0.1,
+            "bad_words_ids": null,
+            "begin_suppress_tokens": null,
+            "bos_token_id": 0,
+            "chunk_size_feed_forward": 0,
+            "classifier_dropout": 0.0,
+            "cross_attention_hidden_size": null,
+            "d_model": 1024,
+            "decoder_attention_heads": 16,
+            "decoder_ffn_dim": 4096,
+            "decoder_layerdrop": 0.0,
+            "decoder_layers": 12,
+            "decoder_start_token_id": 2,
+            "diversity_penalty": 0.0,
+            "do_sample": false,
+            "dropout": 0.1,
+            "early_stopping": false,
+            "encoder_attention_heads": 16,
+            "encoder_ffn_dim": 4096,
+            "encoder_layerdrop": 0.0,
+            "encoder_layers": 12,
+            "encoder_no_repeat_ngram_size": 0,
+            "eos_token_id": 2,
+            "exponential_decay_length_penalty": null,
+            "finetuning_task": null,
+            "forced_bos_token_id": null,
+            "forced_eos_token_id": 2,
+            "id2label": {
+                "0": "LABEL_0",
+                "1": "LABEL_1",
+                "2": "LABEL_2"
+            },
+            "init_std": 0.02,
+            "is_decoder": false,
+            "is_encoder_decoder": true,
+            "label2id": {
+                "LABEL_0": 0,
+                "LABEL_1": 1,
+                "LABEL_2": 2
+            },
+            "length_penalty": 1.0,
+            "max_length": 20,
+            "max_position_embeddings": 4096,
+            "min_length": 0,
+            "model_type": "florence2_language",
+            "no_repeat_ngram_size": 0,
+            "num_beam_groups": 1,
+            "num_beams": 3,
+            "num_hidden_layers": 12,
+            "num_return_sequences": 1,
+            "output_attentions": false,
+            "output_hidden_states": false,
+            "output_scores": false,
+            "pad_token_id": 1,
+            "prefix": null,
+            "problem_type": null,
+            "pruned_heads": {},
+            "remove_invalid_values": false,
+            "repetition_penalty": 1.0,
+            "return_dict": true,
+            "return_dict_in_generate": false,
+            "scale_embedding": false,
+            "sep_token_id": null,
+            "suppress_tokens": null,
+            "task_specific_params": null,
+            "temperature": 1.0,
+            "tf_legacy_loss": false,
+            "tie_encoder_decoder": false,
+            "tie_word_embeddings": true,
+            "tokenizer_class": null,
+            "top_k": 50,
+            "top_p": 1.0,
+            "torch_dtype": null,
+            "torchscript": false,
+            "typical_p": 1.0,
+            "use_bfloat16": false,
+            "use_cache": true,
+            "vocab_size": 51289
+        },
+        "torch_dtype": "float32",
+        "vision_config": {
+            "_attn_implementation_autoset": false,
+            "_name_or_path": "",
+            "add_cross_attention": false,
+            "architectures": null,
+            "bad_words_ids": null,
+            "begin_suppress_tokens": null,
+            "bos_token_id": null,
+            "chunk_size_feed_forward": 0,
+            "cross_attention_hidden_size": null,
+            "decoder_start_token_id": null,
+            "depths": [
+                1,
+                1,
+                9,
+                1
+            ],
+            "dim_embed": [
+                256,
+                512,
+                1024,
+                2048
+            ],
+            "diversity_penalty": 0.0,
+            "do_sample": false,
+            "drop_path_rate": 0.1,
+            "early_stopping": false,
+            "enable_checkpoint": false,
+            "encoder_no_repeat_ngram_size": 0,
+            "eos_token_id": null,
+            "exponential_decay_length_penalty": null,
+            "finetuning_task": null,
+            "forced_bos_token_id": null,
+            "forced_eos_token_id": null,
+            "id2label": {
+                "0": "LABEL_0",
+                "1": "LABEL_1"
+            },
+            "image_feature_source": [
+                "spatial_avg_pool",
+                "temporal_avg_pool"
+            ],
+            "image_pos_embed": {
+                "max_pos_embeddings": 50,
+                "type": "learned_abs_2d"
+            },
+            "is_decoder": false,
+            "is_encoder_decoder": false,
+            "label2id": {
+                "LABEL_0": 0,
+                "LABEL_1": 1
+            },
+            "length_penalty": 1.0,
+            "max_length": 20,
+            "min_length": 0,
+            "model_type": "davit",
+            "no_repeat_ngram_size": 0,
+            "num_beam_groups": 1,
+            "num_beams": 1,
+            "num_groups": [
+                8,
+                16,
+                32,
+                64
+            ],
+            "num_heads": [
+                8,
+                16,
+                32,
+                64
+            ],
+            "num_return_sequences": 1,
+            "output_attentions": false,
+            "output_hidden_states": false,
+            "output_scores": false,
+            "pad_token_id": null,
+            "patch_padding": [
+                3,
+                1,
+                1,
+                1
+            ],
+            "patch_prenorm": [
+                false,
+                true,
+                true,
+                true
+            ],
+            "patch_size": [
+                7,
+                3,
+                3,
+                3
+            ],
+            "patch_stride": [
+                4,
+                2,
+                2,
+                2
+            ],
+            "prefix": null,
+            "problem_type": null,
+            "projection_dim": 1024,
+            "pruned_heads": {},
+            "remove_invalid_values": false,
+            "repetition_penalty": 1.0,
+            "return_dict": true,
+            "return_dict_in_generate": false,
+            "sep_token_id": null,
+            "suppress_tokens": null,
+            "task_specific_params": null,
+            "temperature": 1.0,
+            "tf_legacy_loss": false,
+            "tie_encoder_decoder": false,
+            "tie_word_embeddings": true,
+            "tokenizer_class": null,
+            "top_k": 50,
+            "top_p": 1.0,
+            "torch_dtype": null,
+            "torchscript": false,
+            "typical_p": 1.0,
+            "use_bfloat16": false,
+            "visual_temporal_embedding": {
+                "max_temporal_embeddings": 100,
+                "type": "COSINE"
+            },
+            "window_size": 12
+        },
+        "vocab_size": 51289
+    },
+    "tokenizer_name": "facebook/bart-large",
+    "tokenizer_max_length": 1024,
+    "tokenizer_padding_side": "right",
+    "pad_language_to": "max_length",
+    "hidden_size": 1024,
+    "depth": 24,
+    "num_heads": 16,
+    "mlp_ratio": 4.0,
+    "num_domains": 30,
+    "len_soft_prompts": 32,
+    "dim_time": 32,
+    "max_len_seq": 512,
+    "use_hetero_proj": false,
+    "action_mode": "ee6d",
+    "num_denoising_steps": 10,
+    "use_proprio": true,
+    "max_state_dim": 20,
+    "domain_feature_key": null,
+    "resize_imgs_with_padding": [
+        224,
+        224
+    ],
+    "num_image_views": 3,
+    "empty_cameras": 1,
+    "optimizer_lr": 0.0001,
+    "optimizer_betas": [
+        0.9,
+        0.95
+    ],
+    "optimizer_eps": 1e-08,
+    "optimizer_weight_decay": 0.0001,
+    "optimizer_grad_clip_norm": 10.0,
+    "scheduler_warmup_steps": 1000,
+    "scheduler_decay_steps": 30000,
+    "scheduler_decay_lr": 2.5e-06
+}

xvla_libero/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a0e29448111df56b9485cb1f964db799205794c49baeda48ef960589ce649ab
+size 3519073692

xvla_libero/policy_postprocessor.json

@@ -0,0 +1,31 @@
+{
+  "name": "policy_postprocessor",
+  "steps": [
+    {
+      "registry_name": "unnormalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              20
+            ]
+          }
+        },
+        "norm_map": {
+          "VISUAL": "MEAN_STD",
+          "STATE": "IDENTITY",
+          "ACTION": "IDENTITY"
+        }
+      }
+    },
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "cpu",
+        "float_dtype": null
+      }
+    }
+  ]
+}

xvla_libero/policy_preprocessor.json

@@ -0,0 +1,80 @@
+{
+  "name": "policy_preprocessor",
+  "steps": [
+    {
+      "registry_name": "rename_observations_processor",
+      "config": {
+        "rename_map": {}
+      }
+    },
+    {
+      "registry_name": "to_batch_processor",
+      "config": {}
+    },
+    {
+      "registry_name": "tokenizer_processor",
+      "config": {
+        "max_length": 50,
+        "task_key": "task",
+        "padding_side": "right",
+        "padding": "max_length",
+        "truncation": true,
+        "tokenizer_name": "facebook/bart-large"
+      }
+    },
+    {
+      "registry_name": "xvla_add_domain_id",
+      "config": {
+        "domain_id": 3
+      }
+    },
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "cuda",
+        "float_dtype": null
+      }
+    },
+    {
+      "registry_name": "normalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "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
+            ]
+          },
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              20
+            ]
+          }
+        },
+        "norm_map": {
+          "VISUAL": "IDENTITY",
+          "STATE": "IDENTITY",
+          "ACTION": "IDENTITY"
+        }
+      }
+    }
+  ]
+}