- The Logic Behind the Maximum Entropy Principle
- Impact of prompt masking on LLM agent planning performance
- Iterative Summarization using LLMs
- Planner fine-tuning on synthetic agent trajectories
- From monolithic to modular open LLM agents
- A Look at The First Place Solution of a Dermatology Classification Kaggle Competition
- Implementing JSON mode for open LLMs
- Llama-2 agent with grammar-based sampling of function calls
- LLM Fun: Building a Q&A Bot of Myself
- Application development with large language models
- Future of this Blog
- Bayesian Learning via Stochastic Gradient Langevin Dynamics and Bayes by Backprop
- Training compute-optimal Perceiver AR language models
- Handy ChatGPT Prompts
- A gentle introduction to Rotary Position Embedding