Update README.md

README.md

@@ -1,10 +1,7 @@
 ---
 base_model:
-- IlyaGusev/saiga_nemo_12b
-- elinas/Chronos-Gold-12B-1.0
-- Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-21-09-24
-- MarinaraSpaghetti/NemoMix-Unleashed-12B
-library_name: transformers
+- Moraliane/SAINEMO-reMIX
+library_name: exllamav2
 tags:
 - mergekit
 - merge
@@ -15,6 +12,24 @@ language:
 - ru
 - en
 ---
+# SAINEMO-reMIX-exl2
+Original model: [SAINEMO-reMIX](https://huggingface.co/Moraliane/SAINEMO-reMIX) by [Moraliane](https://huggingface.co/Moraliane)
+
+## Quants
+[4bpw h6 (main)](https://huggingface.co/cgus/SAINEMO-reMIX-exl2/tree/main)  
+[4.5bpw h6](https://huggingface.co/cgus/SAINEMO-reMIX-exl2/tree/4.5bpw-h6)  
+[5bpw h6](https://huggingface.co/cgus/SAINEMO-reMIX-exl2/tree/5bpw-h6)  
+[6bpw h6](https://huggingface.co/cgus/SAINEMO-reMIX-exl2/tree/6bpw-h6)  
+[8bpw h8](https://huggingface.co/cgus/SAINEMO-reMIX-exl2/tree/8bpw-h8)  
+
+## Quantization notes
+Made with Exllamav2 0.2.8 with default dataset. This seems to be a Russian RP and perhaps a general-purpose model.  
+It can be used with TabbyAPI, Text-Generation-WebUI with RTX GPU (Windows) or RTX/ROCm (Linux).  
+The model has to fully fit your VRAM for optimal performance. If it doesn't fit, use GGUF version instead.  
+
+Для использования требуется TabbyAPI или Text-Generation-WebUI и видеокарта RTX (Windows) или RTX/ROCm (Linux).  
+Модели в exl2 формате должны помещаться в видеопамять видеокарты.  
+Если видеопамяти недостаточно, то лучше использовать модели в GGUF формате.
 # SAINEMO-reMIX
 ![SAINEMO-reMIX](./remixwife.webp)