Create README.md

README.md

@@ -0,0 +1,18 @@
+---
+license: llama2
+language:
+- en
+---
+
+[EXL2](https://github.com/turboderp/exllamav2/tree/master#exllamav2) Quantization of [l2-13b-thespurral-v1](https://huggingface.co/Setiaku/l2-13b-thespurral-v1).
+
+GGUF [here](https://huggingface.co/Setiaku/l2-13b-thespurral-v1-GGUF)
+
+## Model details
+
+Quantized at [5.33bpw](https://huggingface.co/R136a1/l2-13b-thespurral-v1-exl2/tree/main) and [6.13bpw](https://huggingface.co/R136a1/l2-13b-thespurral-v1-exl2/tree/6bit)
+
+This model is very good (at least for me) for role-playing, I liked it a lot. Visit the [model repo](https://huggingface.co/Setiaku/l2-13b-thespurral-v1) for more details.
+
+
+![cato](https://huggingface.co/R136a1/l2-13b-thespurral-v1-exl2/resolve/main/Cato.png)