Beyond the Parameter Monolith: Modular Language Modeling - a Bochkov Collection

Bochkov 's Collections

Beyond the Parameter Monolith: Modular Language Modeling

Do Language Models Need a Trainable Input Embedding Table?

Language Models Without a Trainable Input Embedding Table

Emergent Semantics Beyond Token Embeddings

Growing Transformers:Layer-wise Expansion Comparative Study

Beyond the Parameter Monolith: Modular Language Modeling

updated 28 days ago

This collection is provided for reproducibility of the paper's main claim

Bochkov/fem-multi-mesh-1p7b

Text Generation • 2B • Updated 9 days ago • 689
Bochkov/modular-reasoning-0p5b-g6p5-demo

Text Generation • 0.5B • Updated 9 days ago • 675
Beyond the Parameter Monolith: Reconstructive Memories, Executable Skills, and Residual Assembly for Language Models

Paper • 2610.04012 • Published Oct 2 • 3