MLX
Safetensors
mixtral
trl
orpo
Generated from Trainer
zephyr-orpo-141b-A35b-v0.1-8bit / model-00008-of-00029.safetensors

Commit History

5b387b23ff0e6c05c79fa80c262c4ba79dfe7fab6ccbb5b0a0c2b1dfa329b0f6
895fdf0
verified

versae commited on