[Merged] Experimental merge model Collection This model merges the adapter learned with LoRa into the original model. • 5 items • Updated about 10 hours ago • 1
[AlternateTokenizer] Collection A series of modified tokenizers for tuning chatml inspired by teknium and hermes. • 3 items • Updated about 10 hours ago • 1
Best of the Rest Collection If you only try one of my models, make it one of these. • 3 items • Updated Sep 27, 2024 • 2
Francois-Huali Collection A finetune ontop of the original Francois-PE model that incorporates KTO to increase coherency and prose. The model aims to have short and sweet prose • 3 items • Updated 9 days ago • 1
FuseChat 3.0 Collection Preference Optimization for Implicit Model Fusion • 13 items • Updated 3 days ago • 11