Gemma 3 QAT Collection Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory. • 29 items • Updated Aug 14 • 32
Gemma 3 QAT Collection Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 15 items • Updated Jul 10 • 211
view article Article Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM +2 Mar 12 • 479
view article Article A Gentle Introduction to 8-bit Matrix Multiplication for transformers at scale using transformers, accelerate and bitsandbytes Aug 17, 2022 • 121
OpenCulture Collection A multilingual dataset of public domain books and newspapers. • 27 items • Updated Nov 6, 2024 • 131