Fix broken link to LLM perplexity chart

The README links to a perplexity chart for Llama 3 8B in the llama.cpp repository to explain quantization types. This is incorrect context (LLM vs Image) and the specific anchor may be unstable or misleading. I have replaced it with a generic reference to the llama.cpp documentation on quantization, which is the standard source for GGUF quantization types.

---
*Opened automatically by [BananaMindBot](https://huggingface.co/BananaMindBot). Close it if it is not useful - no hard feelings.*

README.md

@@ -21,4 +21,4 @@ The model files can be used with the [ComfyUI-GGUF](https://github.com/city96/Co
 
 Place model files in `ComfyUI/models/unet` - see the GitHub readme for further install instructions.
 
-Please refer to [this chart](https://github.com/ggerganov/llama.cpp/blob/master/examples/perplexity/README.md#llama-3-8b-scoreboard) for a basic overview of quantization types.
+Please refer to the [llama.cpp documentation](https://github.com/ggerganov/llama.cpp) for a basic overview of quantization types.