PinnedTeja GollapudiinVMware Data & ML BlogEfficient Instruction Fine-tuning of Flan-UL2 (20B LLM) Using LoRA with Limited ComputeFlan-UL2-Alpaca-LoRA7 min read·Apr 7, 2023----
PinnedTeja GollapudiinVMware Data & ML BlogPretraining a custom BERT modelPython Library to help users pretrain their custom BERT model3 min read·Jul 11, 2022----
Teja GollapudiinVMware Data & ML BlogStarter LLM for the Enterprise: Instruction Tuning OpenLLaMA 7B and 13B(EDIT: Added the 13B model)2 min read·Jun 9, 2023----
Teja GollapudiinVMware Data & ML BlogEnhancing Flan-UL2 with Alpaca to Follow Free-Form InstructionsInstruction tuning on smaller models has demonstrated ChatGPT-like generative capabilities while requiring significantly lower compute…5 min read·Apr 13, 2023----