Update README.md

README.md

@@ -1,3 +1,22 @@
+## Description
+
+Quantified [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2/tree/main) into F16 and converted to LLaMa CPP (GGUF) format.
+
+### About GGUF
+
+GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
+
+## Prompt template: ChatML
+
+```
+<|im_start|>system
+{system_message}<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+
+```
+
 ---
 license: apache-2.0
 ---