Create README.md

README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- llama
+- chat
+- Q3_K_M
+- 7b
+---
+
+This is a converted model to GGUF from `NousResearch/Llama-2-7b-chat-hf` quantized to `Q3_K_M` using `llama.cpp` library.