Update README.md

README.md

@@ -3,4 +3,14 @@ license: gemma
 base_model:
 - ifable/gemma-2-Ifable-9B
 pipeline_tag: text-generation
----
+---
+
+## Llama.cpp imatrix quants of gemma-2-Ifable-9B
+
+Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3804">b3804</a> for quantization.
+
+Original model: https://huggingface.co/ifable/gemma-2-Ifable-9B
+
+All quants made using the imatrix option with the dataset from [here](https://gist.github.com/tristandruyen/9e207a95c7d75ddf37525d353e00659c) and with a context size of 8192.
+
+I also uploaded the BF16 GGUF because I'm too lazy to make every single quant and also in case the original model gets taken down.