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.*
