Very cool blog by @character_ai diving into how they trained their proprietary model Kaiju (13B, 34B, 110B), before switching to OSS model, and spoiler: it has...
threadreaderapp.comยท1d
๐Python
Flag this post
Show HN: Grizzly โ Memory-Efficient Zip Viewer for macOS with Quick Look Preview
๐Python
Flag this post
Did I just join a Hackathon
๐Category Theory
Flag this post
Evaluating Implicit Biases in LLM Reasoning through Logic Grid Puzzles
arxiv.orgยท1d
๐Category Theory
Flag this post
Adaptation and Fine-tuning with TabPFN for Travelling Salesman Problem
arxiv.orgยท1d
๐ฒBayesian Stats
Flag this post
Categorical Emotions or Appraisals - Which Emotion Model Explains Argument Convincingness Better?
arxiv.orgยท1d
๐Category Theory
Flag this post
Simplex-FEM Networks (SiFEN): Learning A Triangulated Function Approximator
arxiv.orgยท2d
๐Category Theory
Flag this post
Interaction Dynamics as a Reward Signal for LLMs
arxiv.orgยท15h
๐Category Theory
Flag this post
Loading...Loading more...