Update README.md

README.md

@@ -6,13 +6,20 @@ library_name: transformers
 tags:
 - mergekit
 - merge
-
+license: other
+language:
+- en
 ---
-[IQ4 GGUF test quant here](https://huggingface.co/Nitrals-Quants/NightWing3_Virtuoso-10B-v0.2-IQ4_NL-GGUF)
+# This has not yet been extensively tested.
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/0QE2gG0eheTSto_iO-RY0.png)
+
 # Base model: (Falcon3-10B-deepseekv3-distill)[[Virtuoso_Lite]](https://huggingface.co/arcee-ai/Virtuoso-Lite)
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/C6gY9vxCl3_SFzQLpLG0S.png)
 
+[IQ4 GGUF test quant here](https://huggingface.co/Nitrals-Quants/NightWing3_Virtuoso-10B-v0.2-IQ4_NL-GGUF)
+
 # Prompt format: ChatML
 ```
 <|im_start|>system
@@ -46,3 +53,4 @@ parameters:
 dtype: bfloat16
 
 ```
+# Notes: The goal of this merge was to make use of both the falcon3-10B base model I trained earlier (nightwing3) and my more recent training run over Arcee's distillation of DeepSeekV3, using falcon3-10B as a base (Virtuoso-Lite-chatmlified-10B_r16-ep1). Initially, I wasn't entirely satisfied with the results of either model on their own. However, with limited testing, this merged version appears to have smoothed out some of the rough edges present in the originals. Further evaluation is needed to fully assess its performance.