Update app.py

app.py

@@ -1,12 +1,13 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
-"""
-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")
+# Load DeepSeek-R1 model and tokenizer
+MODEL_NAME = "deepseek-ai/DeepSeek-R1"
 
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, trust_remote_code=True)
 
+# Function to handle chat interactions
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -15,50 +16,45 @@ def respond(
     temperature,
     top_p,
 ):
+    # Construct messages format
     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]})
+    
+    for user_input, bot_response in history:
+        if user_input:
+            messages.append({"role": "user", "content": user_input})
+        if bot_response:
+            messages.append({"role": "assistant", "content": bot_response})
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
+    # Tokenize input
+    input_text = "\n".join([msg["content"] for msg in messages])
+    inputs = tokenizer(input_text, return_tensors="pt")
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+    # Generate response
+    output = model.generate(
+        **inputs,
+        max_length=max_tokens,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+        do_sample=True
+    )
 
-        response += token
-        yield response
+    response_text = tokenizer.decode(output[0], skip_special_tokens=True)
 
+    return response_text
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Gradio Chat 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)",
-        ),
+        gr.Textbox(value="You are a helpful AI assistant.", label="System Message"),
+        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max Tokens"),
+        gr.Slider(minimum=0.1, maximum=2.0, 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"),
     ],
 )
 
-
+# Launch the Gradio app
 if __name__ == "__main__":
     demo.launch()