Thomas Veran's picture

4 3

Thomas Veran

thomve

·

AI & ML interests

RL

Organizations

spaces 1

Rl Benchmark

This project aims to create a benchmark of RL algorithms

models 2

thomve/Qwen3-0.6B-GRPO-test

Updated May 6, 2025

thomve/Qwen2-0.5B-GRPO-test

Updated Feb 12, 2025

datasets 0

None public yet