Vincent Tu

Finetuning Mistral 7B on the Puffin dataset with LoRA.

Fine-tuning Zephyr-7B on AgentInstruct and running inference with W&B.

In this article, I summarize the finding the in the March 31, 2023 paper "A Survey of Large Language Models".

Let's explore some of W&B's model registry and launch features using Google's new Gemma model!

A minimal example of CI/CD for MLOps with Phi-2, GitOps, and W&B.

Up to 65-billion parameters, LLaMA is an open source model more performant than other other LLMs at certain tasks with much less computation.

Exploring what actually works in prompt engineering

In this article, we'll dig into tensors. We'll look at what they are, how to use them, and some of their real-world applications.

In this article, which is part two, we'll be deep diving into LangChain's implementation of generative agents, to better understand what's changed in recent months.

Are there performance advantages to transitioning to PyTorch? I attempt to answer a specific application of this question, for SLEAP: a keypoint estimation task for flies!

In this article, I'll be improving LangChain's generative agents implementation.

In this post, we'll explore two multi-agent LLM libraries - Camel and Langroid!