Update README.md

README.md

@@ -18,26 +18,29 @@ tags:
 - all genres
 - story
 - writing
-- vivid prosing
+- vivid prose
 - vivid writing
 - fiction
 - roleplaying
 - bfloat16
 - swearing
 - rp
+- llama3
+- enhanced quants
+- max quants
+- maxcpu quants
 - horror
-- mistral nemo
 - mergekit
 pipeline_tag: text-generation
 ---
 
-Updates Dec 21 2024: (uploading quants ... refreshed, and new quants):
-- New quants, quanted with the lastest LLAMACPP improvements : Better instruction following, output generation across all quants.
-- New "ARM" quants for machines than can run them. (format: ".../Q4_0_4_4.gguf")
-- All quants have also been upgraded with "more bits" for output tensor and embed for better performance.
-- Specialized additional quants: "max, max-cpu" (will include this in the file name) for quants "Q2K" (max cpu only), "IQ4_XS", "Q6_K" and "Q8_0"
-- "MAX" : output tensor / embed at float 16. (better instruction following/output generation than standard quants)
-- "MAX-CPU" : output tensor / embed at bfloat 16, which forces these on to the CPU (Nvidia cards / other will vary), this frees up vram at cost of token/second and you get better instruction following/output generation too.
+<B>Updates Dec 21 2024: (uploading quants ... refreshed, and new quants):</B>
+- All quants have been "refreshed", quanted with the lastest LLAMACPP improvements : Better instruction following, output generation across all quants.
+- All quants have also been upgraded with "more bits" for output tensor and embed for better performance (this is in addition to the "refresh")
+- New "ARM" quants have been added for machines than can run them. (format: ".../Q4_0_4_4.gguf")
+- New specialized additional quants (in addition to standard): "max, max-cpu" (will include this in the file name) for quants "Q2K" (max cpu only), "IQ4_XS", "Q6_K" and "Q8_0"
+- "MAX": output tensor / embed at float 16. (better instruction following/output generation than standard quants)
+- "MAX-CPU": output tensor / embed at bfloat 16, which forces these on to the CPU (Nvidia cards / other will vary), this frees up vram at cost of token/second and you get better instruction following/output generation too.
 
 <h2>L3-Dark-Planet-8B-GGUF</h2>