Downloads · 30 days
0
RACE_main_gr00t
SeonghoonYu/RACE_main_gr00t
RACE_main_gr00t is a machine learning model from SeonghoonYu. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Fine-tuning recipe (identical across H): stock Isaac-GR00T n1.6-release, embodiment liberopanda with action.deltaindices = range(H), VLM frozen (tunellm=False, tunevisual=False, tunetopllmlayers=0), action head traine…
Access
Public
Updated Sep 5, 2026
Repo size
26.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors26.3 GB · 100%
At a glance
- Access
- Public
- Created
- Sep 5, 2026
- Updated
- Sep 5, 2026
- SHA
- 0061ab43
Model card
From the Hugging Face model README
RACE_main_gr00t — GR00T N1.6 LIBERO checkpoints
| folder | what | action chunk | notes |
|---|---|---|---|
teacher_h8/ | GR00T N1.6-3B fine-tuned on merged LIBERO (4 suites), 30k steps, batch 64 | 8 | starting point for the runs below (original, unmodified) |
ft_h16_20k/ | teacher_h8 → fine-tuned with chunk 16, 20k steps | 16 | |
ft_h24_20k/ | teacher_h8 → fine-tuned with chunk 24, 20k steps | 24 | |
ft_h32_20k/ | teacher_h8 → fine-tuned with chunk 32, 20k steps | 32 |
Fine-tuning recipe (identical across H): stock Isaac-GR00T n1.6-release, embodiment libero_panda
with action.delta_indices = range(H), VLM frozen (tune_llm=False, tune_visual=False, tune_top_llm_layers=0), action head trained (tune_projector/tune_diffusion_model/tune_vlln=True),
global batch 64 on 2 GPUs, lr 1e-4 cosine with 5% warmup, weight decay 1e-5, DeepSpeed ZeRO-2, bf16,
data = IPEC-COMMUNITY/libero_{spatial,object,goal,10}_no_noops_1.0.0_lerobot merged.
Checkpoints hold model weights + config + processor (optimizer state removed).
Original LIBERO (50 episodes/task, executing the whole chunk), 20k step:
| H | Spatial | Object | Goal | Long | Avg |
|---|---|---|---|---|---|
| 16 | 100.0 | 100.0 | 98.6 | 94.9 | 98.4 |
| 24 | 100.0 | 100.0 | 98.4 | 89.6 | 97.0 |
| 32 | 98.6 | 98.8 | 95.7 | 90.2 | 95.8 |
Serving: gr00t/eval/run_gr00t_server.py --model-path <folder> --embodiment-tag LIBERO_PANDA --use-sim-policy-wrapper;
the chunk length is read from the checkpoint's processor config. Note teacher_h8/processor_config.json
carries a letter_box_transform key from a fork; delete it to load with stock n1.6.
- Created
- Sep 5, 2026
- Updated
- Sep 5, 2026