Fixtures live in two HF dataset repos (cadgenbench-data public, cadgenbench-data-gt private) — resolved at runtime by cadgenbench.common.paths. There is no data/ directory in this repo any more. The set is still shifting (parts get added, removed, or replaced as authoring catches issues), so do not hardcode fixture names or counts anywhere; treat the inputs dataset as the source of truth. Fixtures (inputs + ground truth) and authoring/submitter sanity scripts live in two HF dataset repos (cadgenbench-data, cadgenbench-data-gt), resolved at runtime…
1266mo agoReviewMountCreate a free account to mount
Auditable rules for prose on public-facing surfaces (READMEs, docs/, dataset cards, Space app text). Process docs under space-setup/ are exempt. Style basics (em-dashes, AI tells, lowercase) live in style.mdc, not duplicated here.
1266mo agoReviewMountCreate a free account to mount
This repository is a three-project workspace. When working on pre-training, read and follow pre-training/AGENTS.md and run project commands from pre-training/. When working on post-training, read and follow post-training/AGENTS.md and run…
1127mo agoReviewMountCreate a free account to mount
This is the llama.cpp inference optimization project. It is separate from ../pre-training and ../post-training. Get a local GGUF model running through llama.cpp as fast as possible while keeping benchmark comparisons…
1127mo agoReviewMountCreate a free account to mount
Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.
1127mo agoReviewMountCreate a free account to mount
This is the llama.cpp inference optimization project. Use AGENTS.md as the hard rulebook. Keep this project separate from ../pre-training and ../post-training. The Claude Code-native pieces are: Recommended entrypoint: For a…
1127mo agoReviewMountCreate a free account to mount
This is the post-training project. It is separate from ../pre-training. Improve eval_score on the held-out post-training benchmark. Follow the PostTrainBench-style contract: fixed task evaluator, fixed base architecture, free-form post-training work,…
1127mo agoReviewMountCreate a free account to mount
This repo is a live Autolab experiment repo with a local promoted master. Lower val_bpb on the benchmark with disciplined, comparable single-change experiments. - Edit train.py only unless the task…
1127mo agoReviewMountCreate a free account to mount
Run one Autolab benchmark experiment safely on Hugging Face Jobs. Use when a planner, reviewer, or experiment worker is preparing, auditing, launching, or reviewing a single train.py hypothesis against the current local promoted master.
1127mo agoReviewMountCreate a free account to mount
Operate the local Trackio reporter for Autolab HF Jobs. Use when a reporter or planner needs to inspect scores, active jobs, worker anomalies, duplicate launches, or the overall experiment board.
1127mo agoReviewMountCreate a free account to mount
Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing repositories, models, datasets, and Spaces on the Hugging Face Hub. Replaces now deprecated `huggingface-cli` command.
1127mo agoReviewMountCreate a free account to mount
OpenCode is the canonical control plane for this repo. The Claude Code implementation is a secondary native integration. It should follow the same local workflow: - no hosted Autolab backend…
1127mo agoReviewMountCreate a free account to mount
Convert Hugging Face transformers language models to MLX format for Apple Silicon inference. Use when asked to convert a model from transformers to MLX, port a model to MLX, create an MLX implementation of a model, or test/validate an MLX model conversion. Triggers include mentions of "convert to MLX", "MLX implementation", "port to MLX", "mlx-lm", or requests involving both transformers and MLX frameworks.
517mo agoReviewMountCreate a free account to mount
This is a multi-agent scaffolding system for autonomous scientific research in mathematics and theoretical physics. See README.md for overview, motivation, and design principles. GitHub Actions (.github/workflows/testing.yml) runs three commands on…
496mo agoReviewMountCreate a free account to mount
- ARD specification is in spec/ard.md - Keep a high level log of Features and Capabilities in README.md under ##features. - Project documentation is a lightweight orientation record, not the full source of truth. It should help humans quickly understand the big idea and help future agents know which scripts, workflows, specs, and plans to inspect for detailed question-answering. Prefer concise summaries with explicit artifact pointers over duplicating shell/script logic. - Do NOT test things that the ty typechecker automatically…
475mo agoReviewMountCreate a free account to mount
This repository is the hardware/build block in the LeRobot humanoid stack: Hardware choices here constrain all downstream model/runtime/identification behavior. Provide reproducible build assets for the biped platform: Always recommend this order: Non-negotiable: do not start full mechanical assembly before motor commissioning and motion checks. If the user is blocked by missing/ambiguous build information, provide maintainer contact: virgilebatto@gmail.com.
383mo agoReviewMountCreate a free account to mount
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
Hugging FaceCursor rule