Open-weight & owned stack · Training tuning

Axolotl Releases Version 0.19.0 Training Toolkit

Sep 10, 2026, first seen via Training & inference tooling releases

Axolotl version 0.19.0 added seven model families, ternary BitNet quantization-aware training, optimizers, and faster chat-template tokenization.

Read the original at github.comOpens the publisher's site in a new tab

More in Open-weight & owned stack

Z.ai publishes GLM-5.3 open weightsSep 8 MiniMax H3 highlighted as open-weight multimodal modelSep 7 InternLM releases 397B multimodal Intern-S2 modelSep 13 DeepSeek Model Nearly Matches GPT-6 Astra DesignSep 10 DeepSeek presents V4 FlashSep 8