Building with Agents, Claude Code, Codex, and ideas.
Pinned Loading
-
nanoreasoner
nanoreasoner PublicKnowledge distillation fails at 158x compression: a systematic negative result with statistical rigor
Python 2
-
distillation-reward-audit
distillation-reward-audit PublicPost-hoc audit of a 22.3σ val_bpb false-positive in a 19M-parameter knowledge distillation experiment. Dual-dimension attribution: token-level gradient + sample-level pass@k.
Python 1
-
-
-
FlashMLA
FlashMLA PublicForked from deepseek-ai/FlashMLA
FlashMLA: Efficient Multi-head Latent Attention Kernels
C++ 1
-
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.




