AI Math that won the Olympiad is open sourced!

NuminaMath is a series of language models that are trained to solve math problems using tool-integrated reasoning (TIR). NuminaMath 7B TIR won the first progress prize of the AI Math Olympiad (AIMO), with a score of 29/50 on the public and private tests sets.

This model is a fine-tuned version of deepseek-ai/deepseek-math-7b-base with two stages of supervised fine-tuning:

• Stage 1: fine-tune the base model on a large, diverse dataset of natural language math problems and solutions, where each solution is templated with Chain of Thought (CoT) to facilitate reasoning.

• Stage 2: fine-tune the model from Stage 1 on a synthetic dataset of tool-integrated reasoning, where each math problem is decomposed into a sequence of rationales, Python programs, and their outputs. Here we followed Microsoft’s ToRA paper and prompted GPT-4 to produce solutions in the ToRA format with code execution feedback. Fine-tuning on this data produces a reasoning agent that can solve mathematical problems via a mix of natural language reasoning and use of the Python REPL to compute intermediate results.
  

Model here: https://huggingface.co/AI-MO/NuminaMath-7B-TIR

_{Reduce Hallucinations?!} 

^{I got a colab for you that attempts to increase factuality with DoLA}

Production RAG

Do you RAG? Then you should get to know about GraphRAG and also some nice chunking techniques and how it can change the metrics.

Btw, What’s your RAG setup like? Any reranker? search? or just a Langchain Q&A?

See you!
Abdul