Pinned Loading

1. can-i-finetune-this can-i-finetune-this Public

   Estimate whether a Hugging Face model fits and fine-tunes on your local GPU.

   Python 457 65

2. pairjudge pairjudge Public

   Pairwise LLM judges (A/B/tie): budget-aware multi-turn packing, position-bias correction, pseudo-label distillation. Generalized from the 4th-place (gold) solution to Kaggle LMSYS Chatbot Arena.

   Python 169 11

3. llm-gpu-lab llm-gpu-lab Public

   One GPU. Full LLM workflow. Real benchmarks. No cloud required.

   Python 25 4

4. mcp-fence mcp-fence Public

   Local-first security scanner, MCP protocol inspector, dynamic fuzzer, Docker sandbox, and report generator for Model Context Protocol servers.

   Python 16 5

5. labelbank labelbank Public

   Retrieve + rerank over a closed label bank: LLM bi-encoders with self-mined hard negatives and a generative listwise reranker. Generalized from a silver-medal solution to Kaggle Eedi — Mining Misco…

   Python 20 2

6. molgen molgen Public

   Lightweight toolkit for de novo molecular generation: SMILES & SELFIES tokenizers, CharRNN / MolGPT / VAE models, training, sampling, and MOSES-style metrics.

   Python 15 4