▲ 2 ▼ Orthrus-Qwen3: up to 7.8×tokens/forward on Qwen3, identical output distribution (github.com) submitted 6 months ago by cm0002@toast.ooo to c/Aii@programming.dev comment fedilink hide all child comments
▲ 10 ▼ Orthrus-Qwen3: up to 7.8×tokens/forward on Qwen3, identical output distribution (github.com) submitted 6 months ago by BB84@mander.xyz to c/localllama@sh.itjust.works 2 comments fedilink hide all child comments Crossposted from https://lemmy.ml/post/47429470 Paper: https://arxiv.org/abs/2605.12825
▲ 9 ▼ Orthrus-Qwen3: up to 7.8×tokens/forward on Qwen3, identical output distribution (github.com) submitted 6 months ago by yogthos@lemmy.ml to c/artificial_intel@lemmy.ml comment fedilink hide all child comments