Upload README.md

README.md

@@ -100,7 +100,7 @@ Generated importance matrix file: [Qwen2.5-Coder-0.5B-Instruct.imatrix.dat](http
 Make sure you are using `llama.cpp` from commit [0becb22](https://github.com/ggerganov/llama.cpp/commit/0becb22ac05b6542bd9d5f2235691aa1d3d4d307) or later.
 
 ```shell
-./llama-cli -ngl 25 -m Qwen2.5-Coder-0.5B-Instruct.IQ4_XS.gguf --color -c 32768 --temp 0.7 --top-p 0.8 --top-k 20 --repeat-penalty 1.05 -p "<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>\n{prompt}<|im_end|>\n<|im_start|>assistant\n"
+./llama-cli -ngl 25 -m Qwen2.5-Coder-0.5B-Instruct.IQ4_NL.gguf --color -c 32768 --temp 0.7 --top-p 0.8 --top-k 20 --repeat-penalty 1.05 -p "<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>\n{prompt}<|im_end|>\n<|im_start|>assistant\n"
 ```
 
 Change `-ngl 25` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.