Update README.md

README.md

@@ -9,15 +9,13 @@ tags:
 # UNA-ThePitbull 21.4B v1
 
 Introducing the best LLM in the industry. Nearly as good as a 70B, just a 21.4B based on saltlux/luxia-21.4b-alignment-v1.0
+![UNA - ThePitbull 21.4B v1](https://huggingface.co/fblgit/UNA-ThePitbull-21.4-v1/resolve/main/UNA-ThePitbull.png)
 
-## UNA Details
-
-Only MLP were Uniformed leaving room for further optimisations.
-You should be able to perform a SFT+DPO again on this model at moderate speeds.
+This model has not been poisoned to score high and be useless. We release him becaues its the real deal of EQ & IQ all together in a crazy powerful smart and conversational model. So far the #1 of them at 25/5/2024
 
 # Evaluations
 
-Can only be compared with its non-una base model. the original luxia-21.4b
+Can only be compared with its non-una base model: the original luxia-21.4b.
 
 ## UNA (VLLM) Evaluations
 ```
@@ -55,4 +53,9 @@ Can only be compared with its non-una base model. the original luxia-21.4b
 |              |       |none            |     0|acc_norm   |0.4003|±  | 0.009|
 |pubmedqa      |      1|none            |     0|acc        |0.6680|±  |0.0211|
 |boolq         |      2|none            |     0|acc        |0.8346|±  |0.0065|
-```
+```
+
+## UNA Details
+
+Only MLP were Uniformed leaving room for further optimisations.
+You should be able to perform a SFT+DPO again on this model at moderate speeds. 1e-4/2e-5/etc.