Update app.py

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 text generation pipeline with the specified model
+pipe = pipeline("text-generation", model="chargoddard/Yi-34B-Llama", device=0)
 
 def respond(
     message,
@@ -27,21 +24,19 @@ def respond(
 
     response = ""
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+    # Generate the response using the pipeline
+    result = pipe(
+        messages[-1]["content"],
+        max_length=max_tokens,
+        num_return_sequences=1,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+    )
 
-        response += token
-        yield response
+    response = result[0]['generated_text']
+    yield response
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Gradio interface setup
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -58,6 +53,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()