remove additional inputs and output text from streamer

app.py

@@ -19,7 +19,7 @@ model = LlavaForConditionalGeneration.from_pretrained(
     model_id,
     torch_dtype=torch.float16,
     low_cpu_mem_usage=True
-).to('cuda')
+).to('cuda:0')
 
 processor = AutoProcessor.from_pretrained(model_id)
 
@@ -27,11 +27,7 @@ model.generation_config.eos_token_id = 128009
 
 @spaces.GPU(duration=120)
 def krypton(input,
-            history,
-            max_new_tokens,
-            temperature,
-            num_beams,
-            do_sample: bool=True):
+            history):
     """
     Recieves inputs (prompts with images if they were added),
     the image is formated for pil and prompt is formated for the model,
@@ -66,17 +62,12 @@ def krypton(input,
     # Streamer
     streamer = TextIteratorStreamer(processor, **{"skip_special_tokens": False, "skip_prompt": True})
 
-    if temperature == 0.0:
-        do_sample = False
-
     # Generation kwargs
     generation_kwargs = dict(
         inputs=inputs,
         streamer=streamer,
-        max_new_tokens=max_new_tokens,
-        temperature=temperature,
-        num_beams=num_beams,
-        do_sample=do_sample
+        max_new_tokens=1024,
+        do_sample=False
     )
 
     thread = threading.Thread(target=model.generate, kwargs=generation_kwargs)
@@ -105,27 +96,27 @@ with gr.Blocks(fill_height=True) as demo:
         fn=krypton,
         chatbot=chatbot,
         fill_height=True,
-        additional_inputs_accordion=gr.Accordion(label="⚙️ Parameters", open=False, render=False),
-        additional_inputs=[
-            gr.Slider(minimum=20,
-                      maximum=80,
-                      step=1,
-                      value=50,
-                      label="Max New Tokens",
-                      render=False),
-            gr.Slider(minimum=0.0,
-                      maximum=1.0,
-                      step=0.1,
-                      value=0.7,
-                      label="Temperature",
-                      render=False),
-            gr.Slider(minimum=1,
-                      maximum=12,
-                      step=1,
-                      value=5,
-                      label="Number of Beams",
-                      render=False),
-        ],
+        # additional_inputs_accordion=gr.Accordion(label="⚙️ Parameters", open=False, render=False),
+        # additional_inputs=[
+        #     gr.Slider(minimum=20,
+        #               maximum=80,
+        #               step=1,
+        #               value=50,
+        #               label="Max New Tokens",
+        #               render=False),
+        #     gr.Slider(minimum=0.0,
+        #               maximum=1.0,
+        #               step=0.1,
+        #               value=0.7,
+        #               label="Temperature",
+        #               render=False),
+        #     gr.Slider(minimum=1,
+        #               maximum=12,
+        #               step=1,
+        #               value=5,
+        #               label="Number of Beams",
+        #               render=False),
+        # ],
         multimodal=True,
         textbox=chat_input,
     )