Gemma 3 QAT Collection Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory. • 19 items • Updated Apr 18 • 28
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 26 days ago • 207
view article Article TTS Arena: Benchmarking Text-to-Speech Models in the Wild By mrfakename and 6 others • Feb 27, 2024 • 71
view article Article SmolVLM2: Bringing Video Understanding to Every Device By orrzohar and 6 others • Feb 20 • 290
view article Article Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM By ariG23498 and 3 others • Mar 12 • 448
view article Article A Gentle Introduction to 8-bit Matrix Multiplication for transformers at scale using transformers, accelerate and bitsandbytes By ybelkada and 1 other • Aug 17, 2022 • 103
OpenCulture Collection A multilingual dataset of public domain books and newspapers. • 27 items • Updated Nov 6, 2024 • 130