Update app.py

app.py

@@ -5,6 +5,7 @@ from huggingface_hub import InferenceClient
 
 client = InferenceClient("Satyam-Singh/LLaVa-Large-Language-Virtual-Assistant")
 
+TITLE = """<h1 align="center">LLaVa Large Language Virtual Assistant</h1>"""
 
 # Set up the model
 generation_config = {
@@ -103,53 +104,76 @@ def gemini_chat(message, history):
     response = convo.send_message(message)
     return response.text
 
-additional_inputs=[
-    gr.Slider(
-        label="Temperature",
-        value=0.9,
-        minimum=0.0,
-        maximum=1.0,
-        step=0.05,
-        interactive=True,
-        info="Higher values produce more diverse outputs",
-    ),
-    gr.Slider(
-        label="Max new tokens",
-        value=4096,
-        minimum=0,
-        maximum=8192,
-        step=64,
-        interactive=True,
-        info="The maximum numbers of new tokens",
-    ),
-    gr.Slider(
-        label="Top-p (nucleus sampling)",
-        value=1,
-        minimum=0.0,
-        maximum=1,
-        step=0.05,
-        interactive=True,
-        info="Higher values sample more low-probability tokens",
-    ),
-    gr.Slider(
-        label="Repetition penalty",
-        value=1,
-        minimum=1.0,
-        maximum=2.0,
-        step=0.05,
-        interactive=True,
-        info="Penalize repeated tokens",
-    )
-]
+run_button_component = gr.Button(value="Run", variant="primary", scale=1)
+temperature_component = gr.Slider(
+    minimum=0,
+    maximum=1.0,
+    value=0.4,
+    step=0.05,
+    label="Temperature",
+    info=(
+        "Temperature controls the degree of randomness in token selection. Lower "
+        "temperatures are good for prompts that expect a true or correct response, "
+        "while higher temperatures can lead to more diverse or unexpected results. "
+    ))
+max_output_tokens_component = gr.Slider(
+    minimum=1,
+    maximum=2048,
+    value=1024,
+    step=1,
+    label="Token limit",
+    info=(
+        "Token limit determines the maximum amount of text output from one prompt. A "
+        "token is approximately four characters. The default value is 2048."
+    ))
+stop_sequences_component = gr.Textbox(
+    label="Add stop sequence",
+    value="",
+    type="text",
+    placeholder="STOP, END",
+    info=(
+        "A stop sequence is a series of characters (including spaces) that stops "
+        "response generation if the model encounters it. The sequence is not included "
+        "as part of the response. You can add up to five stop sequences."
+    ))
+top_k_component = gr.Slider(
+    minimum=1,
+    maximum=40,
+    value=32,
+    step=1,
+    label="Top-K",
+    info=(
+        "Top-k changes how the model selects tokens for output. A top-k of 1 means the "
+        "selected token is the most probable among all tokens in the model’s "
+        "vocabulary (also called greedy decoding), while a top-k of 3 means that the "
+        "next token is selected from among the 3 most probable tokens (using "
+        "temperature)."
+    ))
+top_p_component = gr.Slider(
+    minimum=0,
+    maximum=1,
+    value=1,
+    step=0.01,
+    label="Top-P",
+    info=(
+        "Top-p changes how the model selects tokens for output. Tokens are selected "
+        "from most probable to least until the sum of their probabilities equals the "
+        "top-p value. For example, if tokens A, B, and C have a probability of .3, .2, "
+        "and .1 and the top-p value is .5, then the model will select either A or B as "
+        "the next token (using temperature). "
+    ))
+
 
-examples=[["I'm planning a vacation to Japan. Can you suggest a one-week itinerary including must-visit places and local cuisines to try?", None, None, None, None, None, ],
+examples=[["I'm planning a vacation to India. Can you suggest a one-week itinerary including must-visit places and local cuisines to try?", None, None, None, None, None, ],
           ["Can you write a short story about a time-traveling detective who solves historical mysteries?", None, None, None, None, None,],
           ["I'm trying to learn French. Can you provide some common phrases that would be useful for a beginner, along with their pronunciations?", None, None, None, None, None,],
-          ["I have chicken, rice, and bell peppers in my kitchen. Can you suggest an easy recipe I can make with these ingredients?", None, None, None, None, None,],
+          ["I have paneer, rice, and bell peppers in my kitchen. Can you suggest an easy recipe I can make with these ingredients?", None, None, None, None, None,],
           ["Can you explain how the QuickSort algorithm works and provide a Python implementation?", None, None, None, None, None,],
-          ["What are some unique features of Rust that make it stand out compared to other systems programming languages like C++?", None, None, None, None, None,],
+          ["What are some unique features of Python that make it stand out compared to other systems programming languages like C++,Java?", None, None, None, None, None,],
          ]
 
+gr.HTML(TITLE)
+
 gr.ChatInterface(
     fn=gemini_chat,
     chatbot=gr.Chatbot(show_label=False,
@@ -162,7 +186,6 @@ gr.ChatInterface(
                       ),
     title="LLAVA: Large Language Virtual Assistant",
     description="Official Demo Of ```LLAVA``` based on ```Large Language Virtual Assistant ```.",
-    additional_inputs=additional_inputs,#title="LLaVa 56B Large Language Virtual Assiatant",
     examples=examples,
     concurrency_limit=20,
 ).launch(show_api=True)