Update README.md

README.md

@@ -1 +1,18 @@
-Nemo, but braindamaged and Gutenberged. [Test-1 (private for now)](https://huggingface.co/rAIfle/MN-Test-1-bf16) => c2-low-r LoRA'd ([Test-2 (private for now)](https://huggingface.co/rAIfle/MN-Test-2-bf16)) => GutenbergDPO ([Test-3](https://huggingface.co/The-Company/rAIfle-MN-Test-3-bf16), _you are here_)
+---
+base_model:
+- unsloth/Mistral-Nemo-Base-2407-bnb-4bit
+library_name: transformers
+tags:
+- unsloth
+license: apache-2.0
+---
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6569a4ed2419be6072890cf8/T_ITjuaHakgamjwuElcAs.png)
+
+# Luca-MN-bf16
+
+This thing was just intended as an experiment but it turned out quite good. I had it both name and prompt imagegen for itself.
+
+## Prompting
+
+Use the `Mistral V3-Tekken` context- and instruct-templates. Temperature at about `1.25` seems to be the sweet spot, with either MinP at `0.05` or TopP at `0.9`. DRY/Smoothing etc depending on your preference.