High-performance RLHF/GRPO pipeline scaling Gemma 3 on GKE Ray Clusters (B200/H200) using NVIDIA NeMo-RL. Includes native FSDP checkpoint merging and zero-shot vLLM benchmarking.
-
Updated
Mar 27, 2026 - Shell
#
math-500
Here are 3 public repositories matching this topic...
Deterministic mathematical and symbolic verification environments for Reinforcement Learning with Verifiable Rewards (RLVR).
-
Updated
Oct 4, 2026 - Python
A minimal reasoning pipeline for Qwen3-0.6B where one verifier plays three roles: evaluation, reward, validation.
-
Updated
Oct 2, 2026 - Python
Add this topic to your repo
To associate your repository with the math-500 topic, visit your repo's landing page and select "manage topics."