DedeProGames's picture

Building on HF

DedeProGames PRO

DedeProGames

·

AI & ML interests

Thinking and Agentic Finetuning

Recent Activity

posted an update about 3 hours ago

Introducing GRM-Coder, a 14b params code model based on Qwen3-14b . On LiveCodeBench v6 (01/08/2024 - 01/05/2025), we achieved a Pass@1 accuracy of 67.87%, up 7.08% from the baseline Pass@1 accuracy of 60.79% of Qwen3-14B. https://huggingface.co/OrionLLM/GRM-Coder-14b

updated a model about 3 hours ago

OrionLLM/GRM2-3b

new activity about 13 hours ago

huggingface/InferenceSupport:SL-AI/GRaPE-Mini

View all activity

Organizations

DedeProGames 's datasets 4

DedeProGames/Medical-Reasoning-SFT-Nano

Viewer • Updated 16 days ago • 20k • 418 • 2

DedeProGames/OpenThoughts3-20k

Viewer • Updated 25 days ago • 20k • 23 • 1

DedeProGames/andy-4-mixture

Viewer • Updated Feb 20 • 121k • 32 • 1

DedeProGames/OpenThoughts-114k

Viewer • Updated Feb 20 • 114k • 51 • 1