This is a heavily interactive web application, and JavaScript is required. Simple HTML interfaces are possible, but that is not what this is.
Post
mr. TIM
timkellogg.me
did:plc:ckaz32jwl6t2cno6fmuw2nhn
rStar-Math takes qwen2.5 7b & 1.5b as well as qhi3 3.8b and fine tunes them for math
they’re able to exceed o1-preview on math benchmarks (with the 7B)
the magic sauce seems to be in co-evolving the SLM (the main LLM) and the PPM (Process Preference Model, the verifier)
arxiv.org/abs/2501.04519
https://arxiv.org/abs/2501.04519
2025-01-09T15:14:29.058Z