Update README.md

README.md

@@ -73,6 +73,15 @@ NEO IMATRIX quants are here:
 
 [ https://huggingface.co/DavidAU/L3-Dark-Planet-8B-NEO-Imatrix-GGUF ]
 
+F32 Version (mastered from float32 source files):
+
+[ https://huggingface.co/DavidAU/L3-Dark-Planet-Ring-World-8B-F32-GGUF ]
+
+I suggest downloading quant(s) of both "Bloat16" and "Float32" versions of this model for your use case(s).
+
+The Float32 version has increased detail, "stays in the moment", and slightly higher creativity. However their "character" is different
+from one another too.
+
 This is a LLAMA3 model, and requires Llama3 template, but may work with other template(s) and has maximum context of 8k / 8192. 
 However this can be extended using "rope" settings up to 32k.