Update app.py

app.py

@@ -1,11 +1,10 @@
 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
 
+# Load your model and tokenizer from Hugging Face
+model_name = "YOUR_USERNAME/YOUR_MODEL_NAME"
+model = AutoModelForCausalLM.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
 
 def respond(
     message,
@@ -25,23 +24,11 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
-
-    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
+    inputs = tokenizer(message, return_tensors="pt")
+    outputs = model.generate(**inputs, max_length=max_tokens, temperature=temperature, top_p=top_p)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
 
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -58,6 +45,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()