Downloads · 30 days
0
hybrid-framesamp-simplesubgoal-policy
bingaochen/hybrid-framesamp-simplesubgoal-policy
hybrid-framesamp-simplesubgoal-policy is a robotics model from bingaochen. Use it for the robotics task on the model card, and read the license before you ship it in a product. It is set up for openpi. The card lists the license as mit.
Memory-augmented VLA fine-tuned from the π₀.₅ backbone. Combines a FrameSamp visual-memory pathway with simple-subgoal symbolic conditioning.
Access
Public
Updated May 27, 2026
Repo size
11.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.zip11.9 GB · 100%
At a glance
- Task
- Robotics
- Library
- openpi
- License
- mit
- Access
- Public
- Created
- May 27, 2026
- Updated
- May 27, 2026
- SHA
- 0a5cfc8e
Model card
From the Hugging Face model README
hybrid-framesamp-simplesubgoal-policy
Memory-augmented VLA fine-tuned from the π₀.₅ backbone. Combines a FrameSamp visual-memory pathway with simple-subgoal symbolic conditioning.
- Backbone: π₀.₅ (openpi)
- Action space:
joint_angle(8-dim) - License: MIT
Use
Serve as an openpi policy server:
python scripts/serve_policy.py \
--port=18001 \
policy:checkpoint \
--policy.dir=/path/to/this/ckpt \
--policy.config=mme_vla_suite
The on-disk layout (after unzip 79999.zip):
_CHECKPOINT_METADATA
assets/
params/
- Task
- Robotics
- Library
- openpi
- License
- mit
- Created
- May 27, 2026
- Updated
- May 27, 2026