Update README.md

README.md

@@ -4,7 +4,7 @@ Small enough to easily run on any cpu. Pretty instant on a gpu.
 Used in text-completion mode, from very short input prompts (A, The, A beautiful, The portrait of [...])
 This is not a chatbot.
 
-Settings that I use for a good variety with WizzGPTv5.Q8_0.gguf (178mb) : max_tokens=75, temperature=1.25, top_p=0.90, top_k=40, repeat_penalty=1.4
+Settings that I use for a good variety with WizzGPTv6.Q8_0.gguf (173mb) : max_tokens=75, temperature=1.25, top_p=0.90, top_k=40, repeat_penalty=1.4
 
 GGUF versions for instant generations : https://huggingface.co/mradermacher/WizzGPTv6-GGUF