Update README.md

README.md

@@ -1,5 +1,17 @@
 ---
 license: apache-2.0
+language:
+- en
+tags:
+- creative
+- story
+- writing
+- fiction
+- float32
+- roleplaying
+- rp
+- enhanced
+- space whale
 ---
 [quants uploading in progress]
 
@@ -12,15 +24,17 @@ The goal: Carry forward maximum precision right up to the point where it is "GUF
 
 This includes F32 master file for GGUF too... at a whopping 78 GBs.
 
-Why?
+WHY?
 
-Because the difference between F32 vs BF16 is... 8 DECIMAL places.
+Because the difference between F32 vs BF16 is... over 8 DECIMAL places.
 
 And as each merge / model is modified there are "losses" along the way.
 
 These losses are carried forward and in turn lead to more losses.
 
-Small?
+And decimal points are critical to model performance.
+
+SMALL?
 
 Yes... but multipled by each merge(s), and compression(s): 20 billion times.
 
@@ -29,17 +43,19 @@ Yes... but multipled by each merge(s), and compression(s): 20 billion times.
 At Q2K an impressive drop of 533 points in perplexity. (lower is better)
 (VS: Q2K orginal base model: PPL = 9.8077 +/- 0.06821 )
 
-At Q4KM an incredible drop of 976 points in perplexity.
+At Q4KM a whopping drop of 976 points in perplexity.
 (VS: Q4km orginal base model -> PPL = 8.7858 +/- 0.06074)
 
 At Q6 an awesome drop of 234 points in perplexity. 
 (VS: Q6 orginal base model -> PPL = 8.6070 +/- 0.05907 )
 
-To put this in perspective "Q6" now operates ABOVE the orginal full precision version of "Psyonic-Cetacean-20b".
+To put this in perspective "Q6" now operates ABOVE the orginal full precision version of "Psyonic-Cetacean-20b" 
+and Q4KM operates at close to Q6 level quality.
 
-This because at "Q6" the quant / compressed model is considered to be accurate within "+0.0008 ppl" of the full, uncompressed / unquanted model and it exceeds this by over 200 points.
+This because at "Q6" the quant / compressed model is considered to be accurate within "+0.0008 ppl" of the full, 
+uncompressed / unquanted model and it exceeds this threshold by over 200 points.
 
-<B>The bottom line here is:</b>
+<B>The bottom line here is this:</b>
 
 Higher quality instruction following and output.
 
@@ -49,11 +65,22 @@ Same great model... turbo charged.
 
 This is the first group of remasters.
 
-<B>More Coming soon...</B>
+<B>The FOUR Horsemen:</B>
+
+This repo will be followed by a "reg quant plus" repo, which added additional components into the GGUF (all levels) at floating point 32 
+precision to further increase the sheer creativity and raw AI horsepower.
+
+This process shaves at extra 50-100 points off perplexity... again.
+
+Following this group will be a full float 32 precision Imatrix (including reg quants "imatrixed").
+
+Test results VS org and "ultra" regular quants will be posted when they come in.
+
+Imatrix Plus repo (with the same floating 32 enhancement at "reg quant plus") that will push the limit even more.
 
-It will be followed by a "reg quant plus", which added additional components into the GGUF (all) at floating point 32 
-precision to further increases the sheer creatity and raw AI horsepower.
+Details of all methods (and pitfalls to avoid) employed to make this high precision remasters will be 
+posted shortly along with comparsions of orginal model and new ultra remaster.
 
-Following this group will be a full precision Imatrix, and Imatrix Plus repo that will push the limit even more.
+Thanks again to Jeb Carter, the orginal creator of "Psyonic-Cetacean 20B"
 
-Details of all methods employed to make this high precision remasters will be posted shortly along with comparsions of orginal model and new ultra remaster.
+[ https://huggingface.co/jebcarter/psyonic-cetacean-20B ]