update readme

README.md

@@ -1,3 +1,15 @@
----
-license: mit
----
+# LLaMA 7B - AWQ GGUF
+- Model creator: [Meta](https://huggingface.co/none)
+- Original model: [LLaMA 7B](https://ai.meta.com/blog/large-language-model-llama-meta-ai)
+
+## Description
+
+This repo contains GGUF format model files with AWQ quantizaton support for [Meta's LLaMA 7b](https://ai.meta.com/blog/large-language-model-llama-meta-ai).
+
+
+## About AWQ-GGUF
+
+The model was convert by the combination of [llama.cpp](https://github.com/ggerganov/llama.cpp) and quantization method [AWQ](https://github.com/mit-han-lab/llm-awq)
+
+## How to use models
+Please refer to [the PR](https://github.com/ggerganov/llama.cpp/pull/4593) from llama.cpp for more detail.

config.json

@@ -0,0 +1,3 @@
+{
+    "model_type": "llama"
+}