DedeProGames/Medical-Reasoning-SFT-Nano
Viewer β’ Updated β’ 20k β’ 414 β’ 2
DedeProGames PRO
DedeProGames
PhysiQuanty's profile picture
ZERO-POINT-INTELLIGENCE-LTD's profile picture
Lumi-node's profile pictureΒ·
AI & ML interests
Thinking and Agentic Finetuning
Recent Activity
reacted to theirpost with π€― about 4 hours ago
π₯ GRM2 - The small one that surpasses the big ones.
What if a 3-parameter model can beat a 32-parameter model in every benchmark? We prove that it can.
GRM2 is a 3b params model based on the llama architecture, trained for long reasoning and high performance in complex tasks - the first 3b params model to outperform qwen3-32b in ALL benchmarks, and outperform o3-mini in almost all benchmarks.
π€ Model: https://huggingface.co/OrionLLM/GRM2-3b
The first 3b params model to generate over 1000 lines of code and achieve a score of 39.0 in xBench-DeepSearch-2510.
π Chat with GRM:
https://huggingface.co/spaces/DedeProGames/GRM2-Chat
π Download official GGUFs: https://huggingface.co/OrionLLM/GRM2-3b-GGUF
reacted to theirpost with π€ about 4 hours ago
π₯ GRM2 - The small one that surpasses the big ones.
What if a 3-parameter model can beat a 32-parameter model in every benchmark? We prove that it can.
GRM2 is a 3b params model based on the llama architecture, trained for long reasoning and high performance in complex tasks - the first 3b params model to outperform qwen3-32b in ALL benchmarks, and outperform o3-mini in almost all benchmarks.
π€ Model: https://huggingface.co/OrionLLM/GRM2-3b
The first 3b params model to generate over 1000 lines of code and achieve a score of 39.0 in xBench-DeepSearch-2510.
π Chat with GRM:
https://huggingface.co/spaces/DedeProGames/GRM2-Chat
π Download official GGUFs: https://huggingface.co/OrionLLM/GRM2-3b-GGUF
reacted to theirpost with π₯ about 4 hours ago
π₯ GRM2 - The small one that surpasses the big ones.
What if a 3-parameter model can beat a 32-parameter model in every benchmark? We prove that it can.
GRM2 is a 3b params model based on the llama architecture, trained for long reasoning and high performance in complex tasks - the first 3b params model to outperform qwen3-32b in ALL benchmarks, and outperform o3-mini in almost all benchmarks.
π€ Model: https://huggingface.co/OrionLLM/GRM2-3b
The first 3b params model to generate over 1000 lines of code and achieve a score of 39.0 in xBench-DeepSearch-2510.
π Chat with GRM:
https://huggingface.co/spaces/DedeProGames/GRM2-Chat
π Download official GGUFs: https://huggingface.co/OrionLLM/GRM2-3b-GGUF
Organizations
