Update app.py

app.py

@@ -22,19 +22,19 @@ def generate(prompt, history, temperature=0.9, max_new_tokens=256, top_p=0.95, t
     print("\nPROMPT: \n\t" + formatted_prompt)
 
     # Generate text from the HF inference
-    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
-    output = ""
+    output = client.text_generation(formatted_prompt, **generate_kwargs, details=True, return_full_text=True)
+    #output = ""
 
-    for response in stream:
-        output += response.token.text
-        yield output
+    #for response in stream:
+    #    output += response.token.text
+    #    yield output
     return output
     
 
 
 additional_inputs=[
     gr.Slider( label="Temperature", value=0.9, minimum=0.0, maximum=1.0, step=0.05, interactive=True, info="Higher values produce more diverse outputs", ),
-    gr.Slider( label="Max new tokens", value=256, minimum=0, maximum=1048, step=64, interactive=True, info="The maximum numbers of new tokens", ),
+    gr.Slider( label="Max new tokens", value=150, minimum=0, maximum=250, step=64, interactive=True, info="The maximum numbers of new tokens", ),
     gr.Slider( label="Top-p (nucleus sampling)", value=0.90, minimum=0.0, maximum=1, step=0.05, interactive=True, info="Higher values sample more low-probability tokens", ),
     gr.Slider( label="Top-k", value=50, minimum=0, maximum=100, step=1, interactive=True, info="Limits the number of top-k tokens considered at each step"),
 ]