Update README.md

README.md

@@ -22,9 +22,9 @@ tags:
 
 - Not supported in llama.cpp master; Requires the latest version of the phi3 128k [branch](https://github.com/ggerganov/llama.cpp/pull/7225)
 - quants & imatrix are still in the oven will follow soon TM
-# - quants done with an importance matrix for improved quantization loss
-# - gguf & imatrix generated from bf16 for "optimal" accuracy loss (some say this is snake oil, but it can't hurt)
-# - Wide coverage of different gguf quant types from Q\_8\_0 down to IQ1\_S
+<!-- - quants done with an importance matrix for improved quantization loss -->
+<!-- - gguf & imatrix generated from bf16 for "optimal" accuracy loss (some say this is snake oil, but it can't hurt) -->
+<!-- - Wide coverage of different gguf quant types from Q\_8\_0 down to IQ1\_S -->
 - Quantized with [llama.cpp](https://github.com/ggerganov/llama.cpp) WIP [branch](https://github.com/ggerganov/llama.cpp/pull/7225)
 - Imatrix generated with [this](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) multi-purpose dataset.
   ```