Update README.md

README.md

@@ -30,10 +30,11 @@ This model was created by [jphme](https://huggingface.co/jphme) and is a fine-tu
 This repository contains the model [jphme/Llama-2-13b-chat-german](https://huggingface.co/jphme/Llama-2-13b-chat-german) in GGUF format.
 
 ## Replication Steps
-Clone llama.cpp *(Commit: 9e20231)*, compile it and use the provided `convert.py` file to convert the original model to GGUF with FP16 precision. The converted model will then be used to do further quantization.
+Clone and install llama.cpp *(Commit: 9e20231)* and use the provided `convert.py` file to convert the original model to GGUF with FP16 precision. The converted model will then be used to do further quantization.
 ```
-# Convert original model to FP16 GGUF format
+# Convert original model to GGUF format with FP16 precision
 python3 llama.cpp/convert.py ./original-models/Llama-2-13b-chat-german --outtype f16 --outfile ./converted_gguf/Llama-2-13b-chat-german-GGUF.fp16.bin
+
 # Quantize FP16 GGUF to 8, 5_K_M and 4_K_M bit
 ./llama.cpp/quantize Llama-2-13b-chat-german-GGUF.fp16.bin Llama-2-13b-chat-german-GGUF.q8_0.bin q8_0
 ./llama.cpp/quantize Llama-2-13b-chat-german-GGUF.fp16.bin Llama-2-13b-chat-german-GGUF.q8_0.bin q5_K_M