MLX
Safetensors
mixtral
trl
orpo
Generated from Trainer
zephyr-orpo-141b-A35b-v0.1-8bit / model-00011-of-00029.safetensors

Commit History

657bf750c8b757618fcefae24c5871fed8211f96cb30099c47d673f15d78b2e4
c7bd4bc
verified

versae commited on