Update README.md

README.md

@@ -13,6 +13,20 @@ Lowers quants (SOTA 2 bits) to come if I'm able to make an iMatrix on my config
 
 -----
 
+Edit : Due to a poor CPU (i7-6700k) for AI purpose, and only 36GB of VRAM, I remade Q3_K_S and Q2_K with an small iMatrix of ctx 32 with 25 chunks (so, 640 tokens), and it lowers the perplexity by :
+
+More than 3% in Rope 8 on Q2_K
+
+WinterGoddess-1.4x-limarpv3-70B-L2-32k-Requant-AR-b1924-Q2_K.gguf,-,wikitext,6.2489,512,
+WinterGoddess-1.4x-limarpv3-70B-L2-32k-Requant-AR-b1924-iMat-c32_ch25-Q2_K.gguf,-,wikitext,6.0482,512
+
+More than 1% with Rope 8 on Q3_K_S
+
+WinterGoddess-1.4x-limarpv3-70B-L2-32k-Requant-AR-b1924-Q3_K_S.gguf,-,wikitext,5.6127,512
+WinterGoddess-1.4x-limarpv3-70B-L2-32k-Requant-AR-b1924-iMat-c32_ch25-Q3_K_S.gguf,-,wikitext,5.5461,512
+
+-----
+
 Benchs of the original Q4_K_S quant I found :
 
 Rope 8 10000