Update README.md

README.md

@@ -33,7 +33,7 @@ model-index:
 
 <p>Dedicated to Nev.</p>
 
-<p><b>NOTE: Currently a severe and abnomal degradation of output quality is observed after (at least) FP8_E3M4 and EXL2 quantization. It wasn't the the case with previous versions. It's being investigated. GGUF is unaffected.</b></p>
+<p><b>NOTE: LLM-Compressor quants don't seem to work correctly, quality seems to be much worse than normal. It wasn't the case with previous versions. GGUF and GPTQ seem to be unaffected.</b></p>
 </br>
 <p><b>Version notes for 0.2</b>: Optimized training hyperparameters and increased sequence length. Better instruction following deeper into context and less repetition.</p>