Update README.md

README.md

@@ -15,14 +15,25 @@ datasets:
 - philschmid/test_german_squad
 ---
 # Llama 2 13b Chat German - GGUF
-- Model creator: [jphme](https://huggingface.co/jphme)
-- Original model: [Meta Llama2 13b Chat](https://huggingface.co/meta-llama/Llama-2-13b-chat)
 
+- **File Format:** GGUF
+- **Conversion done with** llama.cpp *(Commit: 9e20231)* 
+- **Quantization Levels:**
+  - 8 Bit
+  - 5_K_M Bit
+  - 4_K_M Bit
+- **Model:** [jphme/Llama-2-13b-chat-german](https://huggingface.co/jphme/Llama-2-13b-chat-german)
+- **Created by:** [jphme](https://huggingface.co/jphme)
+    
 ## Description
+This model was created by [jphme](https://huggingface.co/jphme) and is a finetune of Meta's [Llama2 13b Chat](https://huggingface.co/meta-llama/Llama-2-13b-chat). 
+This repository contains the model [jphme/Llama-2-13b-chat-german](https://huggingface.co/jphme/Llama-2-13b-chat-german) in GGUF format.
 
-This repo contains GGUF format model files for [jphme's Llama 2 13b Chat German](https://huggingface.co/jphme/Llama-2-13b-chat-german).
+___
 
-# Original Model Card of Finetune: Llama 2 13b Chat German
+# Original Model Card
+
+## Llama 2 13b Chat German
 
 **Edit: You can find a Demo (German) [here](https://huggingface.co/spaces/jphme/Llama-2-13b-chat-german-Demo)**