--- license: cc-by-nc-4.0 language: - en --- These are GGUF quantized versions of [NeverSleep/Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss](https://huggingface.co/NeverSleep/Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss). The importance matrix was trained for 1M tokens (2,000 batches of 512 tokens) using `wiki.train.raw`. The IQ2_XXS and IQ2_XS versions are compatible with llama.cpp, version `147b17a` or later.