OpenBezoar: Small, Cost-Effective and Open Models Trained on Mixes of Instruction Data
Research paper by Chandeepa Dissanayake and collaborators. Published 2024-04-18. Topics: instruction fine-tuning, RLHF, DPO, OpenLLaMA, LaMini-LM.
Resource information
- Authors
- Chandeepa Dissanayake, Lahiru Lowe, Sachith Gunasekara, Yasiru Ratnayake
- Research topics
- instruction fine-tuning, RLHF, DPO, OpenLLaMA, LaMini-LM, WizardLM, Evol-Instruct, databricks-dolly-15k, Orca, Flan Collection, GPT-4, QLoRA
- Publication date
- 2024-04-18
- Publication
- arXiv
- Last record update
- Nov 3, 2026