Modelpublic

khanhnd61/impact-so101-multi-task-gguf

sourceHugging Faceapache-2.0updated 19h agoView on Hugging Face

0likes

Model Card

impact-so101-multi-task-gguf

IMPACT as vla.simd GGUF for CPU inference. Each file is self-contained.

File	Converted from
`impact-so101-multi-task.gguf`	khanhnd61/impact_so101-multi-task-clean
`impact-int8-so101-multi-task.gguf`	khanhnd61/impact-int8_so101-multi-task-clean

Serve

Install vla.simd with the serve extra, then:

hf download khanhnd61/impact-so101-multi-task-gguf --local-dir impact-so101-multi-task-gguf
OMP_NUM_THREADS=$CORES vla-simd-serve --model impact \
    --model-dir impact-so101-multi-task-gguf/impact-so101-multi-task.gguf --port 8080 \
    --task "<instruction>"

Any file in the table works as --model-dir.

Rollout

The robot side is lerobot's async client, lerobot-vla-simd:

pip install 'lerobot[async,feetech] @ git+https://github.com/khanhnd61-vr/lerobot@4b33b84296c0880ebce778d69f16a38d33825575'

On the robot, with the arm and both cameras attached:

lerobot-vla-simd --server_address=127.0.0.1:8080 --policy_type=impact \
    --robot.type=so101_follower --robot.port=/dev/ttyACM0 --robot.id=my_arm \
    --robot.cameras="{ front: {type: opencv, index_or_path: 0, width: 640, height: 480, fps: 30}, wrist: {type: opencv, index_or_path: 2, width: 640, height: 480, fps: 30} }" \
    --actions_per_chunk=50 \
    --task="<instruction>"