AI & ML interests
Artificial intelligence
Recent Activity
View all activity
Papers
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning
CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning
Team members 10 private
Organization Card
Chirp chirp!
We’re the DeepReinforce team, fascinated by everything that could lead us toward superintelligence.
We recently raised a little bird named Ornith. You’ll find it lovely. Come give it a try!
models 29
ornith-ai/Ornith-1.5-9B-DFlash
1B • Updated • 229k • 23
ornith-ai/Ornith-1.5-35B-A3B-DFlash
0.4B • Updated • 328k • 30
ornith-ai/Ornith-1.5-397B-DFlash
1B • Updated • 34.3k • 8
ornith-ai/Ornith-1.5-397B-NVFP4
Text Generation • 203B • Updated • 414k • 19
ornith-ai/Ornith-1.5-9B-NVFP4
Text Generation • 7B • Updated • 731k • 16
ornith-ai/Ornith-1.5-35B-A3B-NVFP4
Text Generation • 20B • Updated • 1.1M • 64
ornith-ai/Ornith-1.5-397B-GGUF
Text Generation • 403B • Updated • 1.16M • 45
ornith-ai/Ornith-1.5-35B-A3B-GGUF
Text Generation • 36B • Updated • 3.79M • 518
ornith-ai/Ornith-1.5-9B-GGUF
Text Generation • 9B • Updated • 4.98M • 555
ornith-ai/Ornith-1.5-397B-FP8
Text Generation • 403B • Updated • 330k • 9