Update README.md

README.md

@@ -3,16 +3,17 @@ base_model:
 - lodestones/Chroma1-HD
 ---
 
-**An FP8 scaled version of Chroma1 HD's latest, revised version (rev-0.1).**
+## Info
 
-Just used Clybius' [conversion scripts from their GitHub repo](https://github.com/Clybius/Learned-Rounding) to create those 2 versions:
+An FP8 scaled version of **Chroma1 HD**'s latest, revised version (**rev-0.1**).
+Just used Clybius' [conversion scripts from their GitHub repo](https://github.com/Clybius/Learned-Rounding) to create these 2 versions:
 
 - Chroma1-HD_float8_e4m3fn_scaled_learned_svd
 - Chroma1-HD_float8_e4m3fn_scaled_learned_svd_fast
 
 *Note: I'm not sure why but HF has automatically categorized my version as a finetune for Chroma1 HD which it isn't. Just a scaled version.*
 
-**Info:**
+## More Info
 
 I strongly suggest you download Clybius version if it's available [somewhere in their HF repo](https://huggingface.co/Clybius/models).
 I'll actually remove those here once they upload their own fp8 versions, as I always use theirs.
@@ -20,7 +21,7 @@ It just happened that I wanted to try this new revised Chroma1 HD version 0.1, a
 
 Needless to say all credit goes to **[lodestones](https://huggingface.co/lodestones)** for the amazing model and to **[Clybius](https://huggingface.co/Clybius/models)** for their scaled versions.
 
-**FAQ:**
+## Some More Info
 
 - *Do I have any clue whatsoever regarding optimal parameters or other refinements for the conversion process?*