Instructions to use rsj2003/StreamingWAM-DiT4DiT-LIBERO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Cosmos
How to use rsj2003/StreamingWAM-DiT4DiT-LIBERO with Cosmos:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Download release.json from rsj2003/StreamingWAM-DiT4DiT-LIBERO: direct link, hf CLI and curl.
- Browser
- Download file 2.68 kB
-
https://huggingface.co/rsj2003/StreamingWAM-DiT4DiT-LIBERO/resolve/main/release.json
- Command line
-
hf download hf://rsj2003/StreamingWAM-DiT4DiT-LIBERO/release.json
-
curl -L -o release.json https://huggingface.co/rsj2003/StreamingWAM-DiT4DiT-LIBERO/resolve/main/release.json
2.68 kB
| { | |
| "model_repo": "rsj2003/StreamingWAM-DiT4DiT-LIBERO", | |
| "model_revision": "v1", | |
| "upstream": { | |
| "code": "https://github.com/Mondo-Robotics/DiT4DiT", | |
| "revision": "66a6f3a12e2c8740157c1e478795952c040d31dd", | |
| "model": "mondo-robotics/dit4dit-model", | |
| "checkpoint": "dit4dit_libero/final_model/pytorch_model.pt", | |
| "sha256": "10cdc70029d84519942157ff741fe570a78f161be3fda6ff1e87286b4c7faa29", | |
| "video_backbone": "nvidia/Cosmos-Predict2.5-2B", | |
| "video_backbone_revision": "diffusers/base/post-trained", | |
| "diffusers_revision": "3996788b602eaae4da41a1d45726b62e662b73cf" | |
| }, | |
| "training": { | |
| "additional_optimizer_steps": 10000, | |
| "global_batch_size": 64, | |
| "schedule_steps": 20000, | |
| "seed": 42, | |
| "future_actions": 8, | |
| "equal_floating_point_compute": false | |
| }, | |
| "evaluation": { | |
| "expected_episodes": 10030, | |
| "manifest_sha256": "e593f5226f2f56f10d54bd0b55fb0bc05e9780d55caef1900982f291d1587464", | |
| "state_manifest_sha256": "9d825aa89a4c0ae34bea517f0a53a1e14a8f6916d0216e47882ad62611cf0629", | |
| "seed": 7, | |
| "execution_steps": 4, | |
| "prompt_protocol": "raw task.language including benchmark suffixes", | |
| "control_hz": 20, | |
| "settling_steps": 5, | |
| "max_steps": 700 | |
| }, | |
| "checkpoints": { | |
| "joint": { | |
| "file": "joint/pytorch_model.pt", | |
| "bytes": 21283251892, | |
| "sha256": "d03fac2a5291a2e2bb518febd4f0ba7c2cafe943ecb8739f1d9f716d832c3b86", | |
| "successful_episodes": 7109, | |
| "total_episodes": 10030, | |
| "success_rate_percent": 70.87736789631107, | |
| "sidecars": { | |
| "config.json": "3a23b790bfc0e349d2f93444a2537f9b84c378c52751989d1a0811e47bf8ce57", | |
| "dataset_statistics.json": "231ed66bcbaa15daa9087b7d256e730ee184cc6cb50a971c6dee7b4eb12c626a", | |
| "inference_config.json": "3f404a913815f64bfbbffe1f2a475960a93a58fab6735fda0466d3365555ec4a", | |
| "training_metadata.json": "1a18541ae40fff177b5d60c40455453dcb7e4d6340257cf335ff9e69db59c940" | |
| } | |
| }, | |
| "streaming": { | |
| "file": "streaming/pytorch_model.pt", | |
| "bytes": 21283251892, | |
| "sha256": "4c34f38f7922dae693b8a3b50735875c0dc81e77d058e46038c694509476dc34", | |
| "successful_episodes": 7660, | |
| "total_episodes": 10030, | |
| "success_rate_percent": 76.37088733798603, | |
| "sidecars": { | |
| "config.json": "7de7888f2546f92f9801fc6f938d97189d1e42c1579ebbb2863a40b4ea973994", | |
| "dataset_statistics.json": "231ed66bcbaa15daa9087b7d256e730ee184cc6cb50a971c6dee7b4eb12c626a", | |
| "inference_config.json": "80c52325b1f4e183cd88b93b6d43dd47871627a7323005a43d3501852246af35", | |
| "training_metadata.json": "1e8b5f2134eed411d727f908e4afc4067ad2b4b656ca879588ed1b68be6a63fe" | |
| } | |
| } | |
| } | |
| } | |