UniRRM-8B
UniRRM-8B is a unified reasoning reward model that supports multiple languages (103 languages) and multiple evaluation paradigms (pairwise,...
UniRRM-8B is a unified reasoning reward model that supports multiple languages (103 languages) and multiple evaluation paradigms (pairwise,...
Qwen3-4B-Base-GRPO — это контрольная точка после RL, обученная с помощью фреймворка verl. Он начинается с Qwen3-4B-Base и применяет...
— Developed by: [More Information Needed] — Funded by [optional]: [More Information Needed] — Shared by [optional]: [More...
Built by Forward AI Labs We are an AI company that provides recruitment agents. | mira.day MQR-A1 rewrites...
Эта модель представляет собой контрольную точку Q DKL** MINT, точно настроенную из Qwen/Qwen3-4B для многооборотного эмпатического диалога. MINT,...
Luna is a conversational AI model designed for immersive roleplay (RP) and natural chatting. It has been carefully...
Модель с параметрами 120B, настроенная с помощью GRPO (Group Relative Policy Optimization) для генерации ядра GPU. Эта модель...
A LoRA adapter for Qwen2.5-14B-Instruct fine-tuned using Distributional Reinforcement Learning for viral headline generation. This model was trained...
We present SciRM and SciRM-Ref, cost-efficient open-source reward models tailored for scientific writing evaluation. Our models are trained...
Модель параметров 1B, обученная с помощью Pure PyTorch GRPO для быстрого и точного выбора инструментов в системах агентного...