Preprint2023
WizardMath
Unknown
WizardMath enhances mathematical reasoning in Llama-2 via Reinforcement Learning from Evol-Instruct Feedback (RLEIF), outperforming many open and closed-source LLMs.
0Aug 1, 2023Reinforcement LearningReasoning
arXiv
AI Research
AI & ML Research Papers
A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
All Papers
3 papersPreprint2023
WizardCoder
Unknown
WizardCoder enhances the open-source Code LLM StarCoder using Code Evol-Instruct to improve code generation performance.
0Jun 1, 2023
Preprint2023
WizardLM
Unknown
Introduces Evol-Instruct, a method to generate large amounts of instruction data with varying complexity using LLMs instead of humans to fine-tune a Llama model.
0Apr 1, 2023Instruction Tuning