Update README.md

README.md

@@ -43,7 +43,7 @@ widget:
 
 ### **review**
 - revised workflow to bypass oom issue and around 50% faster with the new fp8_e4m3fn file
-- t5xxl gguf works fine as text encoder
+- t5xxl works fine as text encoder; more quantized versions of t5xxl can be found [here](https://huggingface.co/chatpig/t5xxl/tree/main)
 - model gguf file might not work; if so, please wait for the code update
 
 ### **reference**