Update README.md

README.md

@@ -105,7 +105,14 @@ This is `BEE-spoke-data/smol_llama-220M-GQA` fine-tuned for code generation on:
 
 This model (and the base model) were both trained using ctx length 2048.  
 
-Example script for inference testing: [here](https://gist.github.com/pszemraj/c7738f664a64b935a558974d23a7aa8c)
+## examples
 
+> Example script for inference testing: [here](https://gist.github.com/pszemraj/c7738f664a64b935a558974d23a7aa8c)
+
+It has its limitations at 220M, but seems decent for single-line or docstring generation, and/or being used for speculative decoding for such purposes.
+
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/60bccec062080d33f875cd0c/bLrtpr7Vi_MPvtF7mozDN.png)
 
 ---