Abhinav Moudgil

This tool is especially useful in cases when evaluations are expensive (e.g. LM harness eval) and you want to track model performance during training.

GitHub - amoudgl/assayer: Python RQ watchdog to automatically evaluate ML model checkpoints offline during training Python RQ watchdog to automatically evaluate ML model checkpoints offline during training - amoudgl/assayer

github: github.com/amoudgl/assa...

New side project!

assayer: A simple Python-RQ based tool to automatically monitor and evaluate ML model checkpoints offline during training.

AuPair: Golden Example Pairs for Code Repair Scaling up inference-time compute has proven to be a valuable strategy in improving the performance of Large Language Models (LLMs) without fine-tuning. An important task that can benefit from additio...

Excited to share our recent work, AuPair, an inference-time technique that builds on the premise of in-context learning to improve LLM coding performance!
arxiv.org/abs/2502.18487

🧵