Update app.py

app.py

@@ -1,18 +1,89 @@
+
+
 import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer
-import torch
 
-# Load the model and tokenizer
-model_name = "Qwen/Qwen2.5-72B-Instruct"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name)
 
-# Define the chat function
-def chatbot(input_text):
-    inputs = tokenizer.encode(input_text, return_tensors="pt")
-    outputs = model.generate(inputs, max_length=150, num_return_sequences=1)
-    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    return response
+import random as rd
+
+
+from huggingface_hub import InferenceClient
+
+
+
+
+
+
+
+client = InferenceClient("Qwen/Qwen2.5-72B-Instruct")
+
+
+def respond (message, history):
+
+
+  messages = [{"role": "system", "content": "You are a chatbot who is sassy and doesnt explain an anser unless someone asks twice."}]
+
+
+
+
+  if history:
+
+
+     messages.extend(history)
+
+
+  messages.append({"role": "user", "content": message})
+
+
+  response = ""
+
+
+  for message in client.chat_completion(
+
+
+       messages,
+
+
+       max_tokens=500,
+
+
+       temperature=0.2,
+
+
+       top_p=0.9,
+
+
+       stream=True
+
+
+   ):
+
+
+       token = message.choices[0].delta.content
+
+
+       response += token
+
+
+       yield response
+
+
+  
+
+
+  
+
+
+chatbot = gr.ChatInterface(respond, type = "messages")
+
+
+chatbot.launch(debug=True)
+
+
+
+
+
+
+
 
 # Define the Gradio interface
 css = """
@@ -22,18 +93,6 @@ css = """
 }
 """
 
-iface = gr.Interface(
-    fn=chatbot,
-    inputs=gr.Textbox(label="You:"),
-    outputs=gr.Textbox(label="Chatbot:"),
-    title="Qwen Chatbot",
-    description="A chatbot using the Qwen/Qwen2.5-72B-Instruct model.",
-    css=css
-)
-
-# Launch the interface
-iface.launch()
-