Update app.py

app.py

@@ -12,12 +12,11 @@ def format_prompt(message, history):
     return prompt
 
 def generate(
-    prompt, history, temperature=0.2, max_new_tokens=30000, top_p=0.95, repetition_penalty=1.0,
+    prompt, history, temperature=0.2, max_new_tokens=30000, top_p=0.9, repetition_penalty=1.0,
 ):
-    temperature = float(temperature)
-    if temperature < 1e-2:
-        temperature = 1e-2
-    top_p = float(top_p)
+    temperature = max(float(temperature), 0.01)
+    top_p = max(min(float(top_p), 1.0), 0.0)
+    repetition_penalty = max(float(repetition_penalty), 0.01)
 
     generate_kwargs = dict(
         temperature=temperature,
@@ -30,12 +29,15 @@ def generate(
 
     formatted_prompt = format_prompt(prompt, history)
 
-    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=True)
-    output = ""
-
-    for response in stream:
-        output += response["generated_text"]
-        yield output
-
-iface = gr.Interface(fn=generate, inputs=["text", "text", "number", "number", "number", "number"], outputs="text", title="Text Generation")
-iface.launch()
+    # Generate text
+    response = client.text_generation(formatted_prompt, **generate_kwargs)
+    generated_text = response["generated_text"]
+    return generated_text
+
+iface = gr.Interface(
+    fn=generate,
+    inputs=["text", "text", gr.inputs.Slider(0.1, 2.0), gr.inputs.Slider(100, 50000), gr.inputs.Slider(0.1, 1.0)],
+    outputs="text",
+    title="Text Generation"
+)
+iface.launch()