Update app.py

app.py

@@ -10,8 +10,8 @@ import spaces
 
 # Load model directly
 device = "cuda" if torch.cuda.is_available() else "cpu"
-tokenizer = AutoTokenizer.from_pretrained("Navid-AI/Yehia-7B", token=os.getenv("HF_TOKEN"))
-model = AutoModelForCausalLM.from_pretrained("Navid-AI/Yehia-7B", torch_dtype=torch.bfloat16, attn_implementation="flash_attention_2", token=os.getenv("HF_TOKEN")).to(device)
+tokenizer = AutoTokenizer.from_pretrained("Navid-AI/Yehia-7B-preview", token=os.getenv("HF_TOKEN"))
+model = AutoModelForCausalLM.from_pretrained("Navid-AI/Yehia-7B-preview", torch_dtype=torch.bfloat16, attn_implementation="flash_attention_2", token=os.getenv("HF_TOKEN")).to(device)
 streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
 
 @spaces.GPU