Update README.md

README.md

@@ -60,13 +60,13 @@ imatrix has no effect on this quant.
 NEO dataset performance improvements will show the most in the IQ4_NL, followed by "MXFP4_MOE" quant.
 
 IQ4_NL quant:
-- OpenAI-120B-NEO2-IQ4_NL.gguf : Standard Imatrix + Output tensor IQ4_NL (NEO Imatrix) AND Embed at IQ4_NL.
+- OpenAI-120B-NEO-IQ4_NL.gguf : Standard Imatrix + Output tensor IQ4_NL (NEO Imatrix) AND Embed at IQ4_NL.
 
-NEO MXFP4_MOE quants:
-- OpenAI-120B-NEO-MXFP4_MOE4.gguf : Output tensor IQ4_NL (NEO Imatrix) AND Embed at IQ4_NL - this makes this quant the smallest version.
+NEO MXFP4_MOE quant:
+- OpenAI-120B-NEO-MXFP4_MOE.gguf : Output tensor IQ4_NL (NEO Imatrix) AND Embed at IQ4_NL - this makes this quant the smallest version.
 
 MXFP4_MOE quants vastly outperform (at the moment) all other quants, except IQ4_NL, Q5_1 and Q8_0 due to odd
-issues compressing OpenAI's 20B model due to odd "tensor" dimensions.
+issues compressing OpenAI's 20B model due to odd "tensor" dimensions (as of this writing).
 
 IQ4_NL, Q5_1 and Q8_0 quants are compatible with OpenAI's tensor structure.