Update app.py

app.py

@@ -2,8 +2,7 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 import torch
 import gradio as gr
 
-# Load model and tokenizer (use public model)
-model_id = "HuggingFaceH4/zephyr-7b-alpha"  # or openchat/openchat-3.5
+model_id = "tiiuae/falcon-rw-1b"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32)
 pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, device=0 if torch.cuda.is_available() else -1)