7 projects
canifinetune
Estimate, benchmark, and generate fine-tuning recipes for LLMs on consumer GPUs.
tracedistill
Distill teacher chains-of-thought into a LoRA adapter via a strict boxed-answer format contract and a two-phase Train→Nudge schedule (silver-medal NVIDIA Nemotron reasoning recipe).
molgen
A lightweight toolkit for de novo molecular generation (SMILES/SELFIES; CharRNN, MolGPT, VAE)
labelbank
Retrieve + rerank over a closed label bank: LLM bi-encoders with self-mined hard negatives and a generative listwise reranker
mcp-fence
Local-first security scanner, MCP protocol inspector, dynamic fuzzer, sandbox runner, and report generator for Model Context Protocol servers.
llm-gpu-lab
One GPU. Full LLM workflow. Real benchmarks. No cloud required.
pairjudge
Train and serve pairwise LLM judges (A/B/tie) with budget-aware multi-turn packing and position-bias correction
