These are 2-bit quantized versions of Aurora Nights 70B v1.0.

The importance matrix was trained for 50K tokens (100 batches of 512 tokens) using wiki.train.raw.

The IQ2_XXS and IQ2_XS versions are compatible with llama.cpp, version 147b17a or later.

GGUF

Unable to determine this model's library. Check the docs .