Update README.md

README.md

@@ -26,18 +26,18 @@ pipeline_tag: text-generation
 
 UPDATE: 
 
-Re-optimizing quants, found a better mixture. Uploading shortly. 
+Re-optimizing quants, found a better mixture. Uploading NOW... 
 
 Mixture is strong enough that lower quants can now solve/reasoning and come up with a solution whereas NON-optimized 
 may not be able to solve or take a lot longer (a lot more tokens!).
 
-Quick testing shows optimized can:
-  - Answer/solve at lower quant.
-  - Come up with a better answer/stronger reasoning
+Quick testing shows optimized quants can:
+  - Answer/solve at lower quant // solve whereas "reg quant" could not.
+  - Come up with a better answer/stronger reasoning.
   - Use less tokens to "reason" ... up to 50% less.
   - Faster and smaller quant size (VS "MAX" with output tensor and embed at BF16).
 
-Quants - "EDGE of REASON":
+<B>Quants - "EDGE of REASON":</B>
 
 IQ1_M - Works, but limited reasoning (reasoning operates, but has a tough time (if at all) coming up with the right answer for some problems).
 
@@ -55,9 +55,12 @@ For TOP performance, Q6/Q8.
 
 ...
 
-All quants have be optimized with:
+All quants (IQ1 right to Q6) have be optimized with:
 
-- NEO Imatrix Dataset
+- NEO Imatrix Dataset. 
+- BF16 Output tensor (full precision)
+
+Q8 (imatrix has no effect on Q8):
 - BF16 Output tensor (full precision)
 
 I found this config worked best with this specific model and "reasoning" in general.