Update README.md

README.md

@@ -1,10 +1,7 @@
 ---
 base_model:
-- IlyaGusev/saiga_nemo_12b
-- Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-21-09-24
-- TheDrummer/Rocinante-12B-v1.1
-- MarinaraSpaghetti/NemoMix-Unleashed-12B
-library_name: transformers
+- Moraliane/NekoMix-12B
+library_name: exllamav2
 tags:
 - mergekit
 - merge
@@ -15,6 +12,29 @@ language:
 - ru
 - en
 ---
+# NekoMix-12B-exl2
+Original model: [NekoMix-12B](https://huggingface.co/Moraliane/NekoMix-12B) by [Moraliane](https://huggingface.co/Moraliane)  
+
+## Quants
+[4bpw h6 (main)](https://huggingface.co/cgus/NekoMix-12B-exl2/tree/main)  
+[4.5bpw h6](https://huggingface.co/cgus/NekoMix-12B-exl2/tree/4.5bpw-h6)  
+[5bpw h6](https://huggingface.co/cgus/NekoMix-12B-exl2/tree/5bpw-h6)  
+[6bpw h6](https://huggingface.co/cgus/NekoMix-12B-exl2/tree/6bpw-h6)  
+[8bpw h8](https://huggingface.co/cgus/NekoMix-12B-exl2/tree/8bpw-h8)  
+
+## Quantization notes
+Made with Exllamav2 0.2.8 with default dataset.  
+It seems to be primarily a Russian RP model. No clue how it performs at all.  
+It can be used with TabbyAPI or Text-Generation-WebUI with RTX GPU on Windows or RTX/ROCm on Linux.  
+Exllamav2 doesn't support offloading to RAM, so make sure it fits your GPU. Otherwise use GGUF quants instead.  
+For example, with 12GB VRAM it can be used at 6bpw/Q6 cache at 16k context.  
+
+Эта модель может использоваться с TabbyAPI или Text-Generation-WebUI.  
+Для работы с ней требуется Nvidia RTX (Windows) или RTX/ROCm (Linux).  
+Exl2 формат требует, чтобы модель полностью помещалась в видеопамяти.  
+Например, с 12ГБ видеопамяти можно использовать 6bpw версию с Q6 кэшем с 16k контекстом.
+
+# Original model card
 # NekoMix-12B
 
 ![NekoMix-12B](./remix.webp)