Direct Preference Optimization: Your Language Model is Secretly a Reward Mode
RLHF is used for aligning language models with human preferences. However, RLHF is a complex and often unstable procedure. Proposed algorithm DPO is stable,...
Recent posts
QLoRA: Efficient Finetuning of Quantized LLMs
Contributions:
Running Jupyter Notebooks in Virtual Environments
As of 2023 November, jupyterlab still does not support working with virtual environments. Using global environment causes all sort of troubles. It is possib...
Granite Foundation Models
Paper provides details about data used in pre-training phase.
LLAMA 2 Paper Notes
This article includes my notes on Llama 2 paper. All images if not stated oherwise are from the paper.