Projects

Free

• Free tool · live

  Loadcheck

  Paste a Hugging Face repo and see whether loading it would run code on your machine. Checks run in your browser.

  Source

• Open-weight model · provenance unverified

  Colibri 8B

  A Llama 3 8B chat model tuned for cybersecurity. Its training-data provenance is unverified and the model card says so — read the card before you use it.

• Open-weight model · provenance unverified

  Colibri 8B · Q5 GGUF

  The Q5 GGUF quantization of Colibri 8B, for running it locally. Same provenance limitation as the source model.

• Public dataset · results page

  BFCL v4 quantization pilot

  We tested four GGUF quantizations on the same 100 selected BFCL V4 cases. Q8_0, Q5_K_M, and Q4_K_M each scored 94/100. Q3_K_M scored 92/100.