Update README.md

README.md

@@ -21,12 +21,17 @@ I have the following Vicuna 1.1 repositories available:
 **13B models:**
 * [Unquantized 13B 1.1 model for GPU - HF format](https://huggingface.co/TheBloke/vicuna-13B-1.1-HF)
 * [GPTQ quantized 4bit 13B 1.1 for GPU - `safetensors` and `pt` formats](https://huggingface.co/TheBloke/vicuna-13B-1.1-GPTQ-4bit-128g)
-* [GPTQ quantized 4bit 13B 1.1 for CPU - GGML format for `llama.cpp`](https://huggingface.co/TheBloke/vicuna-13B-1.1-GPTQ-4bit-128g-GGML)
   
 **7B models:**
 * [Unquantized 7B 1.1 model for GPU - HF format](https://huggingface.co/TheBloke/vicuna-7B-1.1-HF)
 * [GPTQ quantized 4bit 7B 1.1 for GPU - `safetensors` and `pt` formats](https://huggingface.co/TheBloke/vicuna-7B-1.1-GPTQ-4bit-128g)
-* [GPTQ quantized 4bit 7B 1.1 for CPU - GGML format for `llama.cpp`](https://huggingface.co/TheBloke/vicuna-7B-1.1-GPTQ-4bit-128g-GGML)
+
+**GGMLs for CPU inference**
+I removed the GGMLs I originally made for Vicuna 1.1 because they were directly converted GPTQ -> GGML and this seemed to give poor results
+
+Instead I recommend you should use eachadea's GGMLs:
+* [eachadea's Vicuna 13B 1.1 GGML format for `llama.cpp`](https://huggingface.co/eachadea/ggml-vicuna-13b-1.1)
+* [eachadea's Vicuna bB 1.1 GGML format for `llama.cpp`](https://huggingface.co/eachadea/ggml-vicuna-7b-1.1)
 
 ## How to easily download and use this model in text-generation-webui