--- license: other inference: false tags: - gguf - mistral - roleplay --- This repository hosts GGUF-IQ-Imatrix quants for [ResplendentAI/Persephone_7B](https://huggingface.co/ResplendentAI/Persephone_7B). Quants: ```python quantization_options = [ "Q4_K_M", "Q4_K_S", "IQ4_XS", "Q5_K_M", "Q5_K_S", "Q6_K", "Q8_0", "IQ3_M", "IQ3_S", "IQ3_XXS" ] ``` **What does "Imatrix" mean?** It stands for **Importance Matrix**, a technique used to improve the quality of quantized models. The **Imatrix** is calculated based on calibration data, and it helps determine the importance of different model activations during the quantization process. The idea is to preserve the most important information during quantization, which can help reduce the loss of model performance, especially when the calibration data is diverse. [[1]](https://github.com/ggerganov/llama.cpp/discussions/5006) [[2]](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) For imatrix data generation, kalomaze's `groups_merged.txt` with added roleplay chats was used, you can find it [here](https://huggingface.co/Lewdiculous/Datura_7B-GGUF-Imatrix/blob/main/imatrix-with-rp-format-data.txt). This was just to add a bit more diversity to the data. **Steps:** ``` Base⇢ GGUF(F16)⇢ Imatrix-Data(F16)⇢ GGUF(Imatrix-Quants) ``` *Using the latest llama.cpp at the time.* # Original model information: # Persephone ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/626dfb8786671a29c715f8a9/aOnBmqHJQfOFEIgqD_JCz.jpeg) After being in a bit of a rut, I decided to take a radically different approach to produce something new and exciting. It seems to have worked out. I hope you enjoy!