placed sliders for UI

app.py

@@ -26,7 +26,11 @@ model.generation_config.eos_token_id = 128009
 
 @spaces.GPU(duration=120)
 def krypton(input,
-            history):
+            history,
+            max_new_tokens,
+            temperature,
+            num_beams,
+            do_sample: bool=True):
     """
     Recieves inputs (prompts with images if they were added),
     the image is formated for pil and prompt is formated for the model,
@@ -55,12 +59,31 @@ def krypton(input,
     image = Image.open(image)
     # image = Image.open(requests.get(url, stream=True).raw)
     prompt = ("<|start_header_id|>user<|end_header_id|>\n\n<image>\n{input['text']}<|eot_id|>"
-            "<|start_header_id|>assistant<|end_header_id|>\n\n")
+              "<|start_header_id|>assistant<|end_header_id|>\n\n")
     inputs = processor(prompt, image, return_tensors='pt').to('cuda', torch.float16)
-    outputs = model.generate(**inputs, max_new_tokens=200, do_sample=False)
-    output_text = processor.decode(outputs[0], skip_special_tokens=True)
-    print(output_text)
-    return output_text
+
+    # Streamer
+    streamer = TextIteratorStreamer(processor, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
+
+    if temperature == 0.0:
+        do_sample = False
+
+    # Generation kwargs
+    generation_kwargs = dict(
+        inputs=inputs,
+        max_new_tokens=max_new_tokens,
+        temperature=temperature,
+        num_beams=num_beams,
+        do_sample=do_sample
+    )
+
+    thread = threading.Thread(target=model.generate, kwargs=generation_kwargs)
+    thread.start()
+
+    outputs = []
+    for text in streamer:
+        outputs.append(text)
+        yield "".join(outputs)
 
 chatbot=gr.Chatbot(height=600, label="Krypt AI")
 chat_input = gr.MultimodalTextbox(interactive=True, file_types=["image"], placeholder="Enter your question or upload an image.", show_label=False)
@@ -70,6 +93,27 @@ 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),
+        ],
         multimodal=True,
         textbox=chat_input,
     )