Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs Paper • 1802.10026 • Published Oct 30, 2018 • 1
Gemma 4 Collection Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B. • 36 items • Updated 9 days ago • 222
ComfyUI-native DF11 models Collection Note: Only Flux-dev based models work with the official DF11 custom node out-of-the-box. The rest require my custom fork, or patching to work. • 47 items • Updated Apr 20 • 11
The Molecular Structure of Thought: Mapping the Topology of Long Chain-of-Thought Reasoning Paper • 2601.06002 • Published Jan 9 • 60
Base Models Beat Aligned Models at Randomness and Creativity Paper • 2505.00047 • Published Apr 30, 2025 • 3
Canary ASR/AST Collection A collection of multilingual and multitask speech to text models from NVIDIA NeMo 🐤 • 6 items • Updated 12 days ago • 35
Intelligence per Watt: Measuring Intelligence Efficiency of Local AI Paper • 2511.07885 • Published Nov 11, 2025 • 16