Update app.py

app.py

@@ -9,146 +9,47 @@ from threading import Thread
 MODEL_LIST = ["mistralai/Mistral-Nemo-Instruct-2407"]
 HF_TOKEN = os.environ.get("HF_TOKEN", None)
 MODEL = os.environ.get("MODEL_ID")
+# filename: gradio_app.py
 
-TITLE = "<h1><center>Mistral-Nemo</center></h1>"
-
-PLACEHOLDER = """
-<center>
-<p>The Mistral-Nemo is a pretrained generative text model of 12B parameters trained jointly by Mistral AI and NVIDIA.</p>
-</center>
-"""
-
-
-CSS = """
-.duplicate-button {
-    margin: auto !important;
-    color: white !important;
-    background: black !important;
-    border-radius: 100vh !important;
-}
-h3 {
-    text-align: center;
-}
-"""
-
-device = "cpu" # for GPU usage or "cpu" for CPU usage
-
-tokenizer = AutoTokenizer.from_pretrained(MODEL)
-model = AutoModelForCausalLM.from_pretrained(
-    MODEL,
-    torch_dtype=torch.bfloat16,
-    device_map="auto",
-    ignore_mismatched_sizes=True)
-
-@spaces.GPU()
-def stream_chat(
-    message: str, 
-    history: list, 
-    temperature: float = 0.3, 
-    max_new_tokens: int = 1024, 
-    top_p: float = 1.0, 
-    top_k: int = 20, 
-    penalty: float = 1.2,
-):
-    print(f'message: {message}')
-    print(f'history: {history}')
-
-    conversation = []
-    for prompt, answer in history:
-        conversation.extend([
-            {"role": "user", "content": prompt}, 
-            {"role": "assistant", "content": answer},
-        ])
-
-    conversation.append({"role": "user", "content": message})
-
-    input_text=tokenizer.apply_chat_template(conversation, tokenize=False)
-    inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
-    streamer = TextIteratorStreamer(tokenizer, timeout=60.0, skip_prompt=True, skip_special_tokens=True)
+import gradio as gr
+from huggingface_hub import InferenceClient
+
+# Initialize the InferenceClient
+client = InferenceClient(
+    "mistralai/Mistral-Nemo-Instruct-2407",
+    token="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
+)
+
+def chat_with_model(system_prompt, user_message):
+    # Prepare messages for the chat completion
+    messages = [
+        {"role": "system", "content": system_prompt},
+        {"role": "user", "content": user_message}
+    ]
     
-    generate_kwargs = dict(
-        input_ids=inputs, 
-        max_new_tokens = max_new_tokens,
-        do_sample = False if temperature == 0 else True,
-        top_p = top_p,
-        top_k = top_k,
-        temperature = temperature,
-        streamer=streamer,
-        repetition_penalty=penalty,
-        pad_token_id = 10,
-    )
-
-    with torch.no_grad():
-        thread = Thread(target=model.generate, kwargs=generate_kwargs)
-        thread.start()
-        
-    buffer = ""
-    for new_text in streamer:
-        buffer += new_text
-        yield buffer
-
-            
-chatbot = gr.Chatbot(height=600, placeholder=PLACEHOLDER)
-
-with gr.Blocks(css=CSS, theme="Nymbo/Nymbo_Theme") as demo:
-    gr.HTML(TITLE)
-    gr.DuplicateButton(value="Duplicate Space for private use", elem_classes="duplicate-button")
-    gr.ChatInterface(
-        fn=stream_chat,
-        chatbot=chatbot,
-        fill_height=True,
-        additional_inputs_accordion=gr.Accordion(label="⚙️ Parameters", open=False, render=False),
-        additional_inputs=[
-            gr.Slider(
-                minimum=0,
-                maximum=1,
-                step=0.1,
-                value=0.3,
-                label="Temperature",
-                render=False,
-            ),
-            gr.Slider(
-                minimum=128,
-                maximum=8192,
-                step=1,
-                value=1024,
-                label="Max new tokens",
-                render=False,
-            ),
-            gr.Slider(
-                minimum=0.0,
-                maximum=1.0,
-                step=0.1,
-                value=1.0,
-                label="top_p",
-                render=False,
-            ),
-            gr.Slider(
-                minimum=1,
-                maximum=20,
-                step=1,
-                value=20,
-                label="top_k",
-                render=False,
-            ),
-            gr.Slider(
-                minimum=0.0,
-                maximum=2.0,
-                step=0.1,
-                value=1.2,
-                label="Repetition penalty",
-                render=False,
-            ),
-        ],
-        examples=[
-            ["Help me study vocabulary: write a sentence for me to fill in the blank, and I'll try to pick the correct option."],
-            ["What are 5 creative things I could do with my kids' art? I don't want to throw them away, but it's also so much clutter."],
-            ["Tell me a random fun fact about the Roman Empire."],
-            ["Show me a code snippet of a website's sticky header in CSS and JavaScript."],
-        ],
-        cache_examples=False,
-    )
-
-
+    # Collect the response from the model
+    response = ""
+    for message in client.chat_completion(
+            messages=messages,
+            max_tokens=500,
+            stream=True
+    ):
+        response += message.choices[0].delta.content
+    
+    return response
+
+# Create the Gradio interface
+iface = gr.Interface(
+    fn=chat_with_model,
+    inputs=[
+        gr.Textbox(label="System Prompt", placeholder="Enter the system prompt here..."),
+        gr.Textbox(label="User Message", placeholder="Ask a question..."),
+    ],
+    outputs=gr.Textbox(label="Response"),
+    title="Mistral Chatbot",
+    description="Chat with Mistral model using your own system prompts."
+)
+
+# Launch the app
 if __name__ == "__main__":
-    demo.launch()
+    iface.launch(show_api=True, share=False,show_error=True)