First Commit

app.py

@@ -1,11 +1,8 @@
 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")
+from transformers import pipeline
 
+# Initialize the pipeline
+pipe = pipeline("Summarization", model="deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B")
 
 def respond(
     message,
@@ -15,50 +12,69 @@ def respond(
     temperature,
     top_p,
 ):
+    # Format the conversation history
     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_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})
+    
+    # Add the current message
     messages.append({"role": "user", "content": message})
-
+    
+    # Convert messages to a single string format that the model can understand
+    prompt = "\n".join([f"{msg['role']}: {msg['content']}" for msg in messages])
+    
+    # Generate response using the pipeline
     response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+    for output in pipe(
+        prompt,
+        max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
+        stream=True,
     ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+        # Extract the generated text
+        new_text = output[0]['generated_text'][len(response):]
+        response = output[0]['generated_text']
+        yield new_text
 
-
-"""
-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.Textbox(
+            value="You are a friendly and helpful assistant.",
+            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)",
+            label="Top-p (nucleus sampling)"
         ),
     ],
+    title="DeepSeek Chat Interface",
+    description="Chat with the DeepSeek-R1-Distill-Qwen-1.5B model",
 )
 
-
+# Launch the interface
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()