Robotics
Diffusers
Safetensors
LeRobot
lingbot-va
world-model
video-action
galaxea-a1
mango-placement
eef-control
Instructions to use pengyue-polaron/lingbot-va-galaxea-a1-mango-plate-eef-step-100 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use pengyue-polaron/lingbot-va-galaxea-a1-mango-plate-eef-step-100 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("pengyue-polaron/lingbot-va-galaxea-a1-mango-plate-eef-step-100", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - LeRobot
How to use pengyue-polaron/lingbot-va-galaxea-a1-mango-plate-eef-step-100 with LeRobot:
- Notebooks
- Google Colab
- Kaggle
Download training_summary.json from pengyue-polaron/lingbot-va-galaxea-a1-mango-plate-eef-step-100: direct link, hf CLI and curl.
- Browser
- Download file 1.14 kB
-
https://huggingface.co/pengyue-polaron/lingbot-va-galaxea-a1-mango-plate-eef-step-100/resolve/main/training_summary.json
- Command line
-
hf download hf://pengyue-polaron/lingbot-va-galaxea-a1-mango-plate-eef-step-100/training_summary.json
-
curl -L -o training_summary.json https://huggingface.co/pengyue-polaron/lingbot-va-galaxea-a1-mango-plate-eef-step-100/resolve/main/training_summary.json
1.14 kB
| { | |
| "artifact_type": "inference_model", | |
| "checkpoint_step": 100, | |
| "base_model": "robbyant/lingbot-va-base", | |
| "dataset": "pengyue-polaron/nyush-galaxea-a1-fruit-placement-eef-v21", | |
| "dataset_revision": "1bc2c4035e7dc638f7dd9fa5ec7987bec66d0933", | |
| "included_tasks": [ | |
| "put the red mango into the blue plate" | |
| ], | |
| "dataset_episodes": 26, | |
| "dataset_frames": 8783, | |
| "hardware": "2 x NVIDIA A100", | |
| "distributed_strategy": "FSDP full-parameter fine-tuning", | |
| "parameter_dtype": "bfloat16", | |
| "optimizer": "fused AdamW", | |
| "learning_rate": 1e-05, | |
| "warmup_steps": 10, | |
| "adam_beta1": 0.9, | |
| "adam_beta2": 0.95, | |
| "weight_decay": 0.1, | |
| "per_rank_batch_size": 1, | |
| "world_size": 2, | |
| "gradient_accumulation_steps": 8, | |
| "effective_global_batch_size": 16, | |
| "mean_latent_loss": 0.161962, | |
| "mean_action_loss": 0.020129, | |
| "last_50_step_mean_latent_loss": 0.149802, | |
| "last_50_step_mean_action_loss": 0.005676, | |
| "final_latent_loss": 0.1375, | |
| "final_action_loss": 0.0044, | |
| "source_action_dimension": 8, | |
| "model_action_dimension": 30, | |
| "used_action_channel_ids": [0, 1, 2, 3, 4, 5, 6, 28], | |
| "includes_optimizer_state": false | |
| } | |