Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Back to feed
DedeProGames 
posted an update 3 days ago
Post
545
Introducing GRM2, a powerful 3b parameter model designed for long-term reasoning and high performance in complex tasks.

Even with only 3b of parameters, it outperforms qwen3-32b in several benchmarks.

With only 3b of parameters, it can also generate large and complex code of over 1000 lines, use tools in a way comparable to large models, and is perfect for agentic tasks.

GRM2 is licensed under Apache 2.0, making it perfect as a FineTune base for other tasks.

OrionLLM/GRM2-3b
JLouisBiz
•
edited 1 day ago

Is this a truly new model or some other model was used as base?
How was it trained?
Are datasets available?
Any transparency?

·
DedeProGames

Hello JLouisBiz, GRM2 was based on the llama architecture and trained for high reasoning and high performance in general reasoning tasks; however, I cannot reveal much information about GRM2 training.

In this post