Update README.md

README.md

@@ -12,7 +12,7 @@ language:
 ---
 
 Thanks to Gargamel for the compute, to train this!
-<br>It took ~120 Hours on Several A100s.
+<br>It took ~120 Hours on 8x A100s.
 
 ---
 
@@ -25,6 +25,15 @@ This model has went through a single stage finetuning process, over 2 epochs. Da
 - - Dataset consists of a mixture of Human and Claude Data.
 ```
 
+Personal Opinions:
+```
+- Llama 3.1 is... meh. I'm sure you guys in the community have debated over this.
+- Whatever they did to their Instruct overcooked the model. Base is weird compared to Llama 3.
+- Still, the 70B is pretty nice to use, though sometimes it bugs out? A swipe / regen always fixes it.
+- May be less 'uncensored' zero-shot due to removal of c2 samples, but it is perfectly fine for roleplaying purposes.
+- I never got the feeling Euryale was ever too horny, even with v2.1 ymmv.
+```
+
 Prompting Format:
 ```
 - Use the L3 Instruct Formatting - Euryale 2.1 Preset Works Well
@@ -44,13 +53,6 @@ Changes since Euryale v2.1 \[Same Dataset as Stheno 3.4\]
 - Filtered for the usual errors, slop and stuff at the end. Some may have slipped through, but I removed nearly all of it.
 ```
 
-Personal Opinions:
-```
-- Llama 3.1 is... meh. I'm sure you guys in the community have debated over this.
-- Whatever they did to their Instruct overcooked the model. Base is weird.
-- Still, the 70B is pretty nice, though sometimes it bugs out? A swipe / regen always fixes it.
-- May be less 'uncensored' zero-shot due to removal of c2 samples, but it is perfectly fine for roleplaying purposes.
-```
 
 Below are some graphs and all for you to observe.