AI & ML interests

Previously Cognitive Computations - Supervised Fine Tuning, DPO, and unalignment For Dolphin see https://huggingface.co/dphn

Recent Activity

ehartford  updated a model 28 minutes ago
QuixiAI/Kimi-K2-Instruct-BF16
ehartford  published a model about 1 hour ago
QuixiAI/Kimi-K2-Instruct-BF16
ehartford  updated a dataset 6 days ago
QuixiAI/dolphin-distill
View all activity

QuixiAI 's models 89