Research
I've been having a lot of fun trying a wide range of LLM post-training experiments using KerasHub + JAX + TPUs. Might open-source some of th…
On October 11 2026 François Chollet announced that he has been experimenting with large‑language‑model post‑training techniques using KerasHub, JAX, and TPUs. He indicated that portions of his work ma
On October 11 2026 François Chollet announced that he has been experimenting with large‑language‑model post‑training techniques using KerasHub, JAX, and TPUs. He indicated that portions of his work may be open‑source. The tweet attracted more than 8,600 views.
Related
- Lil: Less is Less When Applying Post-Training Sparse-Attention Algorithms in Long-Decode Stage
- The Keras team is gonna be at the AI Systems DevLabs in Sunnvale tomorrow. Come say hi if you're around!
- Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum
Source: Francois Chollet (X) | 2026-10-11