GitLab

---------
Co-authored-by: Patrick Devine <patrick@infrahq.com>

Add native support for converting Qwen2 family models (including Qwen2.5)
from safetensors to gguf format so we can run it.

- FROM /path/to/{safetensors,pytorch}
- FROM /path/to/fp{16,32}.bin
- FROM model:fp{16,32}

Co-authored-by: Michael Yang <mxyng@pm.me>