Update README.md

README.md

@@ -196,6 +196,8 @@ widget:
 
 # Model Summary
 We present GPT-JT, a fork of GPT-6B, trained for 20,000 steps, that outperforms most 100B+ parameter models at classification, and improves most tasks. GPT-JT was trained with a new decentralized algorithm with  1G interconnect.
+GPT-JT is a bidirectional dense model, trained through UL2 objective with NI, P3, COT, the pile data. 
+Please check out our demo: [TOMA-app](https://huggingface.co/spaces/togethercomputer/TOMA-app).
 
 # Quick Start
 ```python