lightly-train
Copilot instructions1.7k starsChanged 19 months agoAGPL-3.0View on GitHub
Follow installation, contributing, and testing instructions from CONTRIBUTING.md in the project root. Always run code in the current virtual environment in .venv/bin/activate unless otherwise specified. When importing: - For classes,…
We split this copilot-instructions.md into the rules it gives an agent
23 rules. About 0 are common, 8 are distinctive, and 15 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
15
Very specific
Tied to their project's names, files or tools. Probably skip.
Licensed with conditions — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 3,669 Copilot instructions files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Trending
Steady talk.thin dataabout the whole repository
Who's talking about lightly-ai/lightly-train
- A Hacker News story“LightlyTrain: Better Vision Models, Faster – No Labels Needed”Hacker News · Apr 15, 2025 · 30 points
- facebookresearch/dinov3“Distill DINOv3 into any Model Architecture”GitHub · Aug 15, 2025 · 11 reactions
- tue-mps/eomt“EoMT with DINOv3”GitHub · Aug 15, 2025 · 11 reactions
- opengeos/geoai“Add support for finetuning DINOv3 for image segmentation”GitHub · Sep 11, 2025 · 4 reactions
- A Hacker News story“Show HN: LightlyTrain – Pretrain YOLO/ResNet on unlabeled data beats ImageNet”Hacker News · Apr 15, 2025 · 3 points
The biggest 5 of 12 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 12
Talked about on GitHub, Hacker News and Bluesky (12 times).
On GitHub · 8
- Aug 15, 2025Distill DINOv3 into any Model Architecture — facebookresearch/dinov311 reactions · 19 comments
- Aug 15, 2025EoMT with DINOv3 — tue-mps/eomt11 reactions · 7 comments
- Sep 11, 2025Add support for finetuning DINOv3 for image segmentation — opengeos/geoai4 reactions · 4 comments
- Apr 2, 2026Fine-tune and distill on custom datasets — facebookresearch/EUPE1 reaction · 7 comments
- Oct 16, 2026[QUESTION] DINOv2 pretraining loss keeps increasing after initial decrease (LightlyTrain 0.17.0) — lightly-ai/lightly0 reactions · 1 comment
3 more on GitHub
- Aug 4, 2026Mypy and numpy incompatible through `make install-dev` — lightly-ai/lightly0 reactions · 7 comments
- Apr 22, 2025Bump lightly from 1.5.19 to 1.5.20 in /requirements — torchgeo/torchgeo0 reactions · 1 comment
- Apr 22, 2025Bump lightly from 1.5.19 to 1.5.20 in /requirements — isaaccorley/torchgeo0 reactions · 1 comment
On Hacker News · 3
- Apr 15, 2025LightlyTrain: Better Vision Models, Faster – No Labels Needed30 points · 11 comments
- Apr 15, 2025Show HN: LightlyTrain – Pretrain YOLO/ResNet on unlabeled data beats ImageNet3 points
- Aug 15, 2025Show HN: Distill DINOv3 into your own model1 point
On Bluesky · 1
- Apr 17, 2025github.com/lightly-ai/lightl... GitHub - lightly-ai/lightly-train: LightlyTrain is the first PyTorch framework to pretrain computer vision… — @technews4869.bsky.social1 likes and repost
Where files are headingNew Copilot instructions files have more rules about branches and pull requests, and fewer about code style.
Of the Copilot instructions files we read, the 2,297 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

