Downloads · 30 days
16
40% of all-time downloads
RLobot-jun/gr00t-n1.7-libero-fewshot-combined-1k
gr00t-n1.7-libero-fewshot-combined-1k is a robotics model from RLobot-jun. 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.
Fine-tuned GR00T N1.7 policy checkpoint. Stage: LIBERO combined few-shot. This stage completed 1,000 optimizer steps with seed 42. This is a policy checkpoint, without a critic head.
Downloads · 30 days
16
40% of all-time downloads
All-time downloads
40
Public
Parameters
3.1B
9.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors9.5 GB · 100%
How the weights are stored.
F321.6B · 52%
From the Hugging Face model README
Fine-tuned GR00T N1.7 policy checkpoint. Stage: LIBERO combined few-shot. This stage completed 1,000 optimizer steps with seed 42. This is a policy checkpoint, without a critic head.
Batch size: 128. Combined LIBERO spatial/object/goal 1-shot (seed 42) and LIBERO-10 5-shot: 80 demonstrations total.
Use the matching GR00T N1.7 training/evaluation implementation. Model weights, configuration, and available processor/normalization metadata are included. Optimizer states, intermediate checkpoints, and training logs are omitted.