How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM? Paper • 2502.14502 • Published 4 days ago • 66 • 8
NousResearch/DeepHermes-3-Llama-3-8B-Preview Text Generation • Updated 5 days ago • 6.15k • 260
mistralai/Mistral-Small-24B-Instruct-2501 Text Generation • Updated 22 days ago • 736k • • 811
Dolphin 3.0 Collection Dolphin 3.0 is the next generation of the Dolphin series of instruct-tuned models. Designed to be the ultimate general purpose local model. • 9 items • Updated 17 days ago • 92
view article Article Unbelievable! Run 70B LLM Inference on a Single 4GB GPU with This NEW Technique By lyogavin • Nov 30, 2023 • 32