These are GGUF quantized versions of 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.
- Downloads last month
- 253
Unable to determine this model's library. Check the
docs
.