Model Distillation

7 posts · 7 sources

CoreweaveBlog1w

Closing the Inference to Post-Training Loop

QdrantBlog1w

Constella Preview: Swap Query Models Without Re-Embedding

Hugging FaceBlog2w

The model that didn't exist, so you made it yourself

LambdaBlog4w

OpenResearcher: a reproducible and scalable pipeline for training deep research agents

Together AIBlog28 Aug

GLM-5.3 vs. GLM-5.3 Flash on DeepSWE: Cost, Coding, and Routing

SpotifyBlog1 Mar

Inside the Archive: The Tech Behind Your 2025 Wrapped Highlights

BasetenBlog7 Jan

A Q&A From Inference To Training: The Inside Story Of Baseten’s Newest Product