minus-squaresamsekhar@alien.topBtoLocalLLaMA•30,000 AI modelslinkfedilinkEnglisharrow-up1·1 year agoIntroduce an interesting work: DARE (Drop And REscale) DARE can merge multiple task-specific LLMs (e.g., WizardLM + WizardMath) into one LM with diverse abilities, ✅but without the need for retraining or GPUs https://twitter.com/WizardLM_AI/status/1727672799391842468?t=alsj7WrhCzVzSxjN7vKOyQ&s=19 linkfedilink
minus-squaresamsekhar@alien.topBtoLocalLLaMA•Open-source LoRa training guide & Code?linkfedilinkarrow-up1·1 year agohttps://github.com/OpenAccess-AI-Collective/axolotl linkfedilink
Introduce an interesting work: DARE (Drop And REscale)
DARE can merge multiple task-specific LLMs (e.g., WizardLM + WizardMath) into one LM with diverse abilities, ✅but without the need for retraining or GPUs
https://twitter.com/WizardLM_AI/status/1727672799391842468?t=alsj7WrhCzVzSxjN7vKOyQ&s=19