Update README.md

README.md

@@ -1,6 +1,5 @@
 ---
 license: mit
-library_name: diffusers
 tags:
 - diffusion
 - llm
@@ -8,6 +7,8 @@ tags:
 - difference-labs
 datasets:
 - smangrul/ultrachat-10k-chatml
+base_model:
+- darwinkernelpanic/DiffReaper-5L
 ---
 
 # DiffReaper-6
@@ -27,4 +28,4 @@ It represents a significant architectural leap over the previous 5L version, tra
 The model is being trained on an RTX 5090 using the `ultrachat-10k` dataset, focusing on conversational flow and instruction following.
 
 ## Goal
-To prove that diffusion models can reach (and eventually exceed) the coherence of auto-regressive models while maintaining the creative "soul" and parallel generation benefits of diffusion.
+To prove that diffusion models can reach (and eventually exceed) the coherence of auto-regressive models while maintaining the creative "soul" and parallel generation benefits of diffusion.