Update app.py

app.py

@@ -1,64 +1,41 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# Load the model and tokenizer
+model_name = "deepseek-ai/DeepSeek-R1"
+model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+
+def respond(message, history: list[tuple[str, str]]):
+    # Prepare the conversation history
+    messages = []
+    for user_msg, assistant_msg in history:
+        if user_msg:
+            messages.append({"role": "user", "content": user_msg})
+        if assistant_msg:
+            messages.append({"role": "assistant", "content": assistant_msg})
     messages.append({"role": "user", "content": message})
 
-    response = ""
+    # Tokenize the input
+    inputs = tokenizer.apply_chat_template(messages, return_tensors="pt")
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+    # Generate the response
+    outputs = model.generate(inputs, max_length=2048, temperature=0.7, top_p=0.95, do_sample=True)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-        response += token
-        yield response
+    return response
 
+# Custom ChatInterface with undo and retry buttons
+def chat_interface(message, history):
+    return respond(message, history)
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Create the Gradio interface
 demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+    fn=chat_interface,
+    retry_btn="Retry",
+    undo_btn="Undo",
+    clear_btn="Clear",
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()