unconst/Affine-5czsc2fc98-r391-offline-dpo-hialpha-hilr-merged Text Generation • 35B • Updated Aug 16 • 6
unconst/Affine-5czsc2fc98-r384-offline-dpo-hialpha-hirank-merged Text Generation • 35B • Updated Aug 16 • 5
unconst/Affine-5czsc2fc98-r386-offline-dpo-hialpha-hirank-hilr-lora Text Generation • Updated Aug 16 • 3
unconst/Affine-5czsc2fc98-r386-offline-dpo-hialpha-hirank-hilr-merged Text Generation • 35B • Updated Aug 16 • 7
unconst/Affine-5czsc2fc98-r371-offline-dpo-hialpha-longctx-merged Text Generation • 35B • Updated Aug 16 • 3
unconst/Affine-5czsc2fc98-r373-offline-dpo-hialpha-longctx-hirank-lora Text Generation • Updated Aug 16 • 7
unconst/Affine-5czsc2fc98-r477-offline-dpo-hialpha-hirank-extrasteps-lora Text Generation • Updated Aug 16 • 4
unconst/Affine-5czsc2fc98-r477-offline-dpo-hialpha-hirank-extrasteps-merged Text Generation • 35B • Updated Aug 16 • 4
unconst/Affine-5czsc2fc98-r478-offline-dpo-hialpha-extrasteps-lora Text Generation • Updated Aug 16 • 4