view article Article Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM Mar 12 • 412
MediTalk-300 Collection MediTalk-300 Collection Models are 4bit finetuned models trainied on a dataset of 1700+ synthetic conversational data about 300+ common diseases. • 3 items • Updated Mar 23
Unsloth 4-bit Dynamic Quants Collection Unsloths Dynamic 4bit Quants selectively skips quantizing certain parameters; greatly improving accuracy while only using <10% more VRAM than BnB 4bit • 28 items • Updated 14 days ago • 80