Downloads · 30 days
15
52% of all-time downloads
gr00t-n1.7-robocasa-bc2-30k
RLobot-jun/gr00t-n1.7-robocasa-bc2-30k
gr00t-n1.7-robocasa-bc2-30k 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: RoboCasa BC2. This stage completed 30,000 optimizer steps with seed 42. This is a policy checkpoint, without a critic head.
All-time downloads
29
Public
Parameters
3.1B
9.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors9.5 GB · 100%
Parameter types
How the weights are stored.
F321.6B · 52%
Model card
From the Hugging Face model README
gr00t-n1.7-robocasa-bc2-30k
Fine-tuned GR00T N1.7 policy checkpoint. Stage: RoboCasa BC2. This stage completed 30,000 optimizer steps with seed 42. This is a policy checkpoint, without a critic head.
Batch size: 32. Tasks: CoffeeSetupMug, PnPCounterToMicrowave, PnPMicrowaveToCounter, TurnOffStove. BC2 continues from the corresponding BC1 checkpoint; 30,000 steps refers to this second stage.
Loading
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.
- Task
- Robotics
- Type
- Gr00tN1d7
- License
- other
- Created
- Sep 21, 2026
- Updated
- Sep 21, 2026