Showing 1–8 of 8

Nov 03PAPERSLoRA in plain English6 min ↗Oct 29PAPERSSparse attention explained: sliding windows, global tokens and block sparsity6 min ↗Oct 11PAPERSSpeculative decoding: faster answers without changing them6 min ↗Oct 02PAPERSScaling laws, in plain English7 min ↗Sep 14PAPERSMixture of experts, without the hype6 min ↗Aug 20PAPERSPreference tuning: RLHF and DPO side by side6 min ↗Jul 26PAPERSTokenizers: the layer everyone ignores until it bites6 min ↗Jul 07PAPERSChain of thought and self-consistency, revisited6 min ↗