Update README.md

README.md

@@ -38,7 +38,7 @@ pipeline_tag: text-generation
 
 <h2>L2-Psyonic-Cetacean-Ultra-Colossal-32B</h2>
 
-<img src="fimv2-grande.jpg" style="float:right; width:300px; height:300px; padding:10px;">
+<img src="psuc.jpg" style="float:right; width:300px; height:300px; padding:10px;">
 
 This is a specialized prose/creative model based in Llama2, max context of 4096 (or 16k+ with rope).
 
@@ -59,7 +59,7 @@ and even how it starts a "reply" / generation too.
 
 This model seems to have a grasp of emotions and how to carefully "write them in" so to speak.
 
-It will also generate close to perfect human like prose.
+It will also generate close to perfect human like prose / capture the "humanity" of the character(s) in the situation.
 
 It may work for role play and other activities. (see settings below)
 
@@ -151,11 +151,21 @@ it may mispell a word (or two) during generation.
 
 So if you are going to use this model for any type of generation, spell check / check in WORD etc etc just in case.
 
+Also note, this is a Llama2 model the brainstorm process pushes right to the wall in terms of performance.
+
+Llama 3, 3.1, Mistral, Mistral Nemo, Solar models performance in stronger than LLama2's.
+
+You can see/download other Brainstorm models by clicking on the Brainstorm Collection on the right of your screen.
+
 <B>Quants:</B>
 
-Currently the only quant uploaded will be Q4_K_M. If you would like other quants uploaded, please open a "ticket" via the "Community Tab", and
+Currently the only quant uploaded will be Q4_K_M. 
+
+If you would like other quants uploaded, please open a "ticket" via the "Community Tab", and
 will upload additional quant(s) based on demand.
 
+This issue is due to slow upload speeds at my end.
+
 <B>Settings, Quants and Critical Operations Notes:</b>
 
 This model has been modified ("Brainstorm") to alter prose output, and generally outputs longer text than average.