Update README.md

README.md

@@ -12,7 +12,7 @@ It is the result of merging the LoRA then saving in HF fp16 format.
 
 * [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/guanaco-13B-GPTQ)
 * [4-bit, 5-bit and 8-bit GGML models for CPU(+GPU) inference](https://huggingface.co/TheBloke/guanaco-13B-GGML)
-* [Original unquantised fp16 model in HF format](https://huggingface.co/TheBloke/guanaco-13B-HF)
+* [Merged, unquantised fp16 model in HF format](https://huggingface.co/TheBloke/guanaco-13B-HF)
   
 # Original model card