MLX
Safetensors
mixtral
trl
orpo
Generated from Trainer
zephyr-orpo-141b-A35b-v0.1-8bit / model-00004-of-00054.safetensors

Commit History

b955b6b35569473d8b6e86a94b978ee62d4ec83568475175e5d291e6ee52800d
44ed11e
verified

versae commited on