Aleph Alpha Blog

DeepSeek Inference Theoretical Model: Deriving the Performance From Hardware Primitives
Introducing TFree-HAT 7B: Tokenizer-Free Models Achieving Top-Tier Multilingual Performance
Breaking Free of Tokenizers: Why We Built T-Free and What It Means for Sovereign AI
Introducing PhariaFiles
A Signature and a Stance: Why We Signed the EU’s General-Purpose AI Code of Practice
Quietly Rebuilt. Boldly Relaunched.
T-Free: Hierarchical Autoregressive Transformers for Language Fairness and Sovereignty
In awe at the scale of these tensors – a gentle introduction to Unit-Scaled Maximal Update Parametrization
Words don’t come easy (… to LLMs): Universal Text-Encoding for dynamic, multi-lingual alphabets revolutionizing efficiency and effectiveness for LLM training and inference
Open-sourcing Codebase Scaling for Non-commercial Research