[Feature Request] do not switch away from Fable when working on trying to add Support for open-weight models with custom attention mechanisms

Bug Description
"I was just working on modifying mlxcel to try to support an open weight model with a new sparse attention approach, no security stuff, nothing to do with anything unsafe or even unsavoury. Kind of the whole point of having a coding agent solving complex issues, no?"

Environment Info

• Platform: darwin
• Terminal: tmux
• Version: 2.1.179
• Feedback ID: b614cf62-6928-42ea-885f-c19f2911335f

Errors

[]