Update app.py

app.py

@@ -15,7 +15,7 @@ class StopOnTokens(StoppingCriteria):
                 return True
         return False
 
-def predict(message, history):
+def predict(message, history, temperature, max_new_tokens, min_new_tokens):
 
     history_transformer_format = history + [[message, ""]]
     stop = StopOnTokens()
@@ -24,15 +24,14 @@ def predict(message, history):
                 for item in history_transformer_format])
 
     model_inputs = tokenizer([messages], return_tensors="pt")
-    streamer = TextIteratorStreamer(tokenizer, timeout=10., skip_prompt=True, skip_special_tokens=True)
     generate_kwargs = dict(
         model_inputs,
-        streamer=streamer,
-        max_new_tokens=1024,
+        max_new_tokens=int(max_new_tokens),
+        min_new_tokens=int(min_new_tokens),
         do_sample=True,
         top_p=1,
         top_k=50,
-        temperature=1.0,
+        temperature=float(temperature),
         num_beams=1,
         stopping_criteria=StoppingCriteriaList([stop])
         )
@@ -46,4 +45,12 @@ def predict(message, history):
             yield partial_message
 
 
-gr.ChatInterface(predict).queue().launch()
+iface = gr.ChatInterface(
+    fn=predict,
+    inputs=["text", "text", gr.Slider(minimum=0.1, maximum=2.0, value=1.0, label="Temperature"),
+            gr.Slider(minimum=1, maximum=2048, value=1024, label="Max Tokens"),
+            gr.Slider(minimum=1, maximum=1024, value=1, label="Min Tokens")],
+    outputs="text"
+)
+
+iface.queue().launch()