Update README.md

README.md

@@ -11,7 +11,7 @@ datasets:
 
 <img src="https://huggingface.co/datasets/tiiuae/documentation-images/resolve/main/falcon_mamba/thumbnail.png" alt="drawing" width="800"/>
 
-**GGUF quantization of [`falcon-mamba-7b-instruct`](https://huggingface.co/tiiuae/falcon-mamba-7b-instruct)**
+**GGUF quantization of [`falcon-mamba-7b-instruct`](https://huggingface.co/tiiuae/falcon-mamba-7b-instruct) in the formats `F16` - `BF16` and `Q8_0`**
 
 #  Table of Contents
 
@@ -40,6 +40,14 @@ datasets:
 
 Refer to the documentation of [`llama.cpp`](https://github.com/ggerganov/llama.cpp) to understand how to run this model locally on your machine.
 
+Download the GGUF weights with the command below:
+
+```bash
+huggingface-cli download tiiuae/falcon-mamba-7b-instruct-GGUF --include FILENAME --local-dir ./
+```
+
+with `FILENAME` being the filename you want to download locally.
+
 # Training Details
 
 ## Training Data