Downloads · 30 days
0
gr00t-n1.7-b1k-multitask-resume
kmy17518/gr00t-n1.7-b1k-multitask-resume
gr00t-n1.7-b1k-multitask-resume is a robotics model from kmy17518. Use it for the robotics task on the model card, and read the license before you ship it in a product. The card lists the license as other.
Full training checkpoints (DeepSpeed ZeRO layout: bf16 model shards + optimizer state in globalstep<N/ + RNG/scheduler state) for resuming the run described in gr00t-n1.7-b1k-multitask.
Access
Public
Updated Jul 25, 2026
Repo size
71.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt57.6 GB · 81%
At a glance
- Task
- Robotics
- License
- other
- Access
- Public
- Created
- Jul 25, 2026
- Updated
- Jul 25, 2026
- SHA
- ff5344da
Base models
Model card
From the Hugging Face model README
GR00T N1.7 — BEHAVIOR-1K 2026 multi-task fine-tune (resume checkpoints)
Full training checkpoints (DeepSpeed ZeRO layout: bf16 model shards + optimizer
state in global_step<N>/ + RNG/scheduler state) for resuming the run described in
gr00t-n1.7-b1k-multitask.
To resume with the wensi-ai/Isaac-GR00T fork: place checkpoint-<N>/ under
outputs/b1k-multitask/ and pass --resume-from-checkpoint to
scripts/b1k/train_b1k.py (the trainer resumes from the highest checkpoint).
- Task
- Robotics
- License
- other
- Created
- Jul 25, 2026
- Updated
- Jul 25, 2026