Update README.md

README.md

@@ -1,3 +1,17 @@
+---
+base_model: mrheinen/Gemma2-27b-lophiid
+tags:
+- llama-cpp
+- gguf-my-repo
+datasets:
+- mrheinen/linux-commands
+---
+
+This is Gemma 27b fine-tuned with https://huggingface.co/datasets/mrheinen/linux-commands
+
+While the normal Gemma will suffice, this version has been fine-tune with more linux commands and was tested with Lophiid to function properly.
+
+
 ---
 base_model: mrheinen/Gemma2-27b-lophiid
 tags:
@@ -47,4 +61,4 @@ Step 3: Run inference through the main binary.
 or 
 ```
 ./llama-server --hf-repo mrheinen/Gemma2-27b-lophiid-Q4_K_M-GGUF --hf-file gemma2-27b-lophiid-q4_k_m.gguf -c 2048
-```
+```