Update app.py

app.py

@@ -8,11 +8,7 @@ import torch
 from transformers import AutoModelForCausalLM, GemmaTokenizerFast, TextIteratorStreamer
 
 DESCRIPTION = """\
-# Gemma 2 2B IT
-Gemma 2 is Google's latest iteration of open LLMs.
-This is a demo of [`google/gemma-2-2b-it`](https://huggingface.co/google/gemma-2-2b-it), fine-tuned for instruction following.
-For more details, please check [our post](https://huggingface.co/blog/gemma2).
-👉 Looking for a larger and more powerful version? Try the 27B version in [HuggingChat](https://huggingface.co/chat/models/google/gemma-2-27b-it) and the 9B version in [this Space](https://huggingface.co/spaces/huggingface-projects/gemma-2-9b-it).
+# Monlam LLM
 """
 
 MAX_MAX_NEW_TOKENS = 2048
@@ -78,43 +74,6 @@ with gr.Blocks(css="style.css", fill_height=True) as demo:
     # Create the chat interface
     chat_interface = gr.ChatInterface(
         fn=generate,
-        additional_inputs=[
-            gr.Slider(
-                label="Max new tokens",
-                minimum=1,
-                maximum=MAX_MAX_NEW_TOKENS,
-                step=1,
-                value=DEFAULT_MAX_NEW_TOKENS,
-            ),
-            gr.Slider(
-                label="Temperature",
-                minimum=0.1,
-                maximum=4.0,
-                step=0.1,
-                value=0.6,
-            ),
-            gr.Slider(
-                label="Top-p (nucleus sampling)",
-                minimum=0.05,
-                maximum=1.0,
-                step=0.05,
-                value=0.9,
-            ),
-            gr.Slider(
-                label="Top-k",
-                minimum=1,
-                maximum=1000,
-                step=1,
-                value=50,
-            ),
-            gr.Slider(
-                label="Repetition penalty",
-                minimum=1.0,
-                maximum=2.0,
-                step=0.05,
-                value=1.2,
-            ),
-        ],
         examples=[
             ["Hello there! How are you doing?"],
             ["Can you explain briefly to me what is the Python programming language?"],
@@ -126,12 +85,6 @@ with gr.Blocks(css="style.css", fill_height=True) as demo:
         type="messages",
     )
     
-    # Create the stop button inside the Blocks context
-    stop_button = gr.Button("Stop", elem_id="stop-btn")
-    stop_button.click(fn=stop_generation, inputs=[], outputs=[])
-
-    gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
-    chat_interface.render()
 
 if __name__ == "__main__":
     demo.queue(max_size=20).launch(share=True)