Update app.py

app.py

@@ -1,11 +1,11 @@
 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 AutoModelForCausalLM, AutoTokenizer
+import torch
 
+# Load your custom model and tokenizer
+MODEL_NAME = "Qwen/Qwen2.5-1.5B-Instruct"  # Replace with your model's Hugging Face repo ID or local path
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, torch_dtype=torch.float16, device_map="auto")
 
 def respond(
     message,
@@ -15,34 +15,38 @@ def respond(
     temperature,
     top_p,
 ):
+    # Prepare the chat 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})
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
+    # Format the input for the model
+    input_text = "\n".join([f"{msg['role']}: {msg['content']}" for msg in messages])
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+    # Generate a response
+    inputs = tokenizer(input_text, return_tensors="pt").to(model.device)
+    outputs = model.generate(
+        inputs.input_ids,
+        max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+        do_sample=True,
+    )
+
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-        response += token
-        yield response
+    # Extract only the assistant's response
+    assistant_response = response.split("assistant:")[-1].strip()
+    yield assistant_response
 
 
-"""
-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=[
@@ -59,6 +63,6 @@ demo = gr.ChatInterface(
     ],
 )
 
-
+# Launch the app
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()