InternRobotics / InternRobotics/VLAC
FYI: Some dependencies are missing.
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 331
- Forks
- 11
- PR merge metrics
- No merged PRs in 30d
Description
Thanks for open sourcing your code :-)
To make example run in fresh conda these additions are necessary:
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -24,7 +24,11 @@ requires-python = ">=3.8"
dependencies = [
"ms-swift==3.3",
"transformers>=4.51.0",
- "peft>=0.15.2"
- "peft>=0.15.2",
- "opencv-python",
- "loguru",
- "timm",
- "flash-attn"
]
For the example to run on 24GB VRAM (4090) reduction to batch_num=8 is necessary. (Maybe use as default in quickstart since this is a common VRAM size)
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the example in a fresh conda environment, then review the dependency list in pyproject.toml and the quickstart settings mentioned in the issue. Done means the listed dependencies are available and the example's default batch_num supports running on a 24GB VRAM GPU.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- build-system, machine-learning, robotics
- Issue type
- Bug
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100