wiio12
Follow
Stars
Technical report of Kimina-Prover Preview.
MoBA: Mixture of Block Attention for Long-Context LLMs
An extremely fast Python package and project manager, written in Rust.
Minimal reproduction of DeepSeek R1-Zero
Fully open reproduction of DeepSeek-R1
A repo lists papers related to LLM based agent
An evaluation benchmark for undergraduate competition math in Lean4, Isabelle, Coq, and natural language.
SymEngine is a fast symbolic manipulation library, written in C++
32 projects in the framework of Deep Reinforcement Learning algorithms: Q-learning, DQN, PPO, DDPG, TD3, SAC, A2C and others. Each project is provided with a detailed training log.
A Machine-to-Machine Interaction System for Lean 4.
A Foreign Function Interface (FFI) to cvc5 solver in Lean.
A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. 🧮✨
A framework for few-shot evaluation of language models.
A simple REPL for Lean 4, returning information about errors and sorries.
A (WIP) equality saturation tactic for Lean based on egg.
A bibliography and survey of the papers surrounding o1
A minimal language for Isabelle/HOL, designed for easing machine learning.
A series of math-specific large language models of our Qwen2 series.
HyperTree Proof Search for Neural Theorem Proving -- "La science est l'œuvre de l'esprit humain, qui est plutôt destiné à étudier qu'à connaître, à chercher qu'à trouver la vérité."
Python for《Deep Learning》，该书为《深度学习》(花书) 数学推导、原理剖析与源码级别代码实现
Codes and Data for Scaling Relationship on Learning Mathematical Reasoning with Large Language Models