OrionLLM/GRM2-3b
4B • Updated • 39 • 4
DedeProGames PRO
DedeProGames
AI & ML interests
Thinking and Agentic Finetuning
Recent Activity
new activity about 3 hours ago
mradermacher/model_requests:SL-AI/CRePE-Mini updated a model about 4 hours ago
OrionLLM/GRM2-3b new activity about 4 hours ago
SL-AI/GRaPE-Mini:GRaPE Mini refuses to load on LM StudiosOrganizations
SL-AI/CRePE-Mini
#2072 opened about 3 hours ago
by DedeProGames
updated a
model about 4 hours ago
GRaPE Mini refuses to load on LM Studios
2
#1 opened about 5 hours ago
by DedeProGames
reactedto salma-remyx's post with 🚀 about 7 hours ago
Post
2809
Looking to execute on your next great idea? 💡
Search for relevant papers and find pre-built Docker images to interactively explore the code with Remyx!
Check out the new space 🔍
remyxai/remyx-explorer
Search for relevant papers and find pre-built Docker images to interactively explore the code with Remyx!
Check out the new space 🔍
remyxai/remyx-explorer
- 2 replies
OrionLLM/GRM2-3b
🤯😎 1
#8789 opened about 7 hours ago
by DedeProGames
upvoted a collection about 7 hours ago
liked 2
models about 7 hours ago
repliedto their post about 7 hours ago
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.
reactedto their post with 🔥🤗 about 7 hours ago
Post
484
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
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
- 2 replies
Used quants, but model is not recognized to support tools, though it does
1
#1 opened about 11 hours ago
by JLouisBiz
CRePE
#2068 opened 1 day ago
by DedeProGames
liked a
model 1 day ago
Welcome to Orion LLM Labs!
3
#1 opened 2 days ago
by DedeProGames
updated a
collection 2 days ago
liked a
model 2 days ago
posted an update 2 days ago
Post
484
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
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
- 2 replies
reactedto ZennyKenny's post with 👀🔥 2 days ago
Post
3096
🤔 So we're supposed to post our repo storage graphs now right?