Exl2 quantized versions of https://huggingface.co/KoboldAI/LLaMA2-13B-TiefighterLR using the pippa dataset (RP oriented) at 4096 length from TheBloke discord server.
Inference API (serverless) is not available, repository is disabled.
Exl2 quantized versions of https://huggingface.co/KoboldAI/LLaMA2-13B-TiefighterLR using the pippa dataset (RP oriented) at 4096 length from TheBloke discord server.