Update README.md

README.md

@@ -50,7 +50,6 @@ widget:
 - full set gguf works on gguf-node (see the last item from reference below)
 - get more **t5xxl-old** gguf encoder either [here](https://huggingface.co/calcuis/pig-encoder/tree/main) or [here](https://huggingface.co/chatpig/t5-v1_1-xxl-old-encoder-gguf/tree/main)
 - note (for internal use) - `ex`: extra state excluded; `ex3`: ex + pos_embedder x 3 excluded
-- for `iq3_s` and `iq3_xxs`, will automatically push to numpy for line-by-line dequant (slow)
 
 ### **reference**
 - base model from [nvidia](https://huggingface.co/nvidia)