| license: apache-2.0 | |
| language: | |
| - en | |
| These are GGUF quantized versions of [notstoic/Nous-Hermes-2-Mixtruct-v0.1-8x7B-DPO-DARE_TIES](https://huggingface.co/notstoic/Nous-Hermes-2-Mixtruct-v0.1-8x7B-DPO-DARE_TIES). | |
| 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. |