Upload README.md

README.md

@@ -14,6 +14,14 @@ tags:
  - Lewdiculous's superb gguf version, thank you for your conscientious and responsible dedication.
  - https://huggingface.co/LWDCLS/llama3-8B-DarkIdol-2.2-Uncensored-1048K-GGUF-IQ-Imatrix-Request
 
+# These are my own quantizations (updated almost daily).
+The difference with normal quantizations is that I quantize the output and embed tensors to f16.
+and the other tensors to 15_k,q6_k or q8_0.
+This creates models that are little or not degraded at all and have a smaller size.
+They run at about 3-6 t/sec on CPU only using llama.cpp
+And obviously faster on computers with potent GPUs
+
+- the fast cat at [ZeroWw/llama3-8B-DarkIdol-2.2-Uncensored-1048K-GGUF](https://huggingface.co/ZeroWw/llama3-8B-DarkIdol-2.2-Uncensored-1048K-GGUF)
 
 ## Why 1048K? 
 Due to the optimization of the preferred model, its performance is excellent across the range of 2000-1048K. Personal usage scenarios, such as 8186, 32K, etc., are insufficient. My primary role involves managing virtual idol Twitter accounts and assisting with singing, etc. A good conversation can be very lengthy, and sometimes even 32K is not enough. Imagine having a heated chat with your virtual girlfriend, only for it to abruptly cut off—that feeling is too painful.