|
Download src/InternVLA-M1/README.md from Tinghong-Ye22/code-Psi0-yth-v21: direct link, hf CLI and curl.
- Browser
- Download file 911 Bytes
-
https://huggingface.co/Tinghong-Ye22/code-Psi0-yth-v21/resolve/main/src/InternVLA-M1/README.md
- Command line
-
hf download hf://Tinghong-Ye22/code-Psi0-yth-v21/src/InternVLA-M1/README.md
-
curl -L -o README.md https://huggingface.co/Tinghong-Ye22/code-Psi0-yth-v21/resolve/main/src/InternVLA-M1/README.md
911 Bytes
InternVLA-M1
Env Setup
Install the env
cd src/InternVLA-M1; uv sync --python 3.10
On Real Data:
- training
cd src/InternVLA-M1
bash scripts/train_internvla.sh # will generate stats_gr00t.json in $TASK/meta/ folder
- serving a checkpoint
cd src/InternVLA-M1
bash scripts/deploy_internvla.sh
On Sim Data:
- download sim data
huggingface-cli download --repo-type dataset USC-PSI-Lab/psi-data --include simple/G1WholebodyBendPick-v0-psi0.zip --local-dir $DATA_DIR
- train on sim data
cd src/InternVLA-M1
bash scripts/train_internvla.sh # will generate stats_gr00t.json in $TASK/meta/ folder
- serving a checkpoint
cd src/InternVLA-M1
bash scripts/deploy_internvla_sim.sh
- launch the eval client
follow the instructions in examples/simple/README.md and replace the
policywithinternvla_m1to launch the eval client