We Got Claude to Fine-Tune an Open Source LLM

We Got Claude to Build CUDA Kernels and teach open models!

Why Claude Code Time Estimates Are Poor

The article titled "Why Claude Code Time Estimates Are Poor" discusses the challenges and shortcomings of using Claude, an LLM, for estimating code development time. It highlights how these estimates can be unreliable and offers insights into improving communication when working with LLM programming tools.

The NLP Course is becoming the LLM Course

Fine-tune Any LLM from the Hugging Face Hub with Together AI

Open-source LLMs as LangChain Agents

Judge Arena: Benchmarking LLMs as Evaluators

Open LLM Leaderboard: DROP deep dive

StarCoder: A State-of-the-Art LLM for Code

Open-Source Text Generation & LLM Ecosystem at Hugging Face

Jupyter Agents: training LLMs to reason with notebooks

Introducing the Open Leaderboard for Hebrew LLMs!

How to Fine-Tune an LLM: An End-to-End Guide

The article "How to Fine-Tune an LLM: An End-to-End Guide" offers a practical, hands‑on walkthrough for fine‑tuning large language models in real‑world scenarios. It covers the entire process from data preparation to deployment, providing readers with actionable steps to adapt LLMs to specific tasks. The guide is aimed at practitioners looking to implement fine‑tuning in a structured, end‑to‑end manner.