Update app.py

app.py

@@ -1,19 +1,16 @@
 import gradio as gr
 # Use a pipeline as a high-level helper
-# Use a pipeline as a high-level helper
-# Use a pipeline as a high-level helper
 from transformers import pipeline
 
-pipe = pipeline("text-generation", model="Qwen/Qwen-7B", trust_remote_code=True)
-"""
-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
-"""
+pipe = pipeline("text-generation", model="tiiuae/falcon-7b", trust_remote_code=True)
+# Load model directly
 # Load model directly
 # Load model directly
 # Load model directly
-from transformers import AutoModelForCausalLM
-model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B", trust_remote_code=True)
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
+tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon-7b", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("tiiuae/falcon-7b", trust_remote_code=True)
 def respond(
     message,
     history: list[tuple[str, str]],