Update app.py

app.py

@@ -56,13 +56,22 @@ def chat(message: str, history: list, stm_state: torch.Tensor, llm_history: list
 with gr.Blocks(title="RxT-Beta-Micro-AI 270M (Supervised) Demo") as demo:
     gr.Markdown("""
     # RxT-Beta-Micro-Supervised 290M vs Stateless LLM Reference 275M
-    Compare Experimental Reactive Transformer with Stateless LLM Reference, trained on the same limited 10B tokens dataset.
+    Compare Experimental Reactive Transformer with Stateless LLM Reference, trained on the same limited real-world data.
+
+    Both models were pre-trained on 10B tokens from english wikipedia and FineWeb-edu, then fine-tuned on 1.1M single interactions
+    and on 30k filtered multi-turn conversations.
+
+    That's very small amount of pre-training data, compared to 1T/2T tokens in production small LLMs. Experiment is made to prove
+    that RxT is learning faster and achieve better results, even after very short training.
+
+    Accuracy (next token prediction) in multi-turn conversation training (validation dataset):
+    - RxT 88%
+    - LLM 60%
 
     ## Limitations
     Supervised version of the model is still in intermediate stage and will be further improved
     in Reinforcement Learning stages (demo will be constantly updated), so model could generate
-    inaccurate answers and memory retention is weak. However, it should still demonstate the architecture
-    advantages, especially infinite context and no delays (small delays are caused by Spaces ZeroGPU allocation).
+    inaccurate answers and memory retention is weak.
     """)
 
     with gr.Row():