Update app.py

app.py

@@ -16,8 +16,8 @@ DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 # Load the model and tokenizer
-tokenizer = GemmaTokenizerFast.from_pretrained("TenzinGayche/example_v1.0.2")
-model = AutoModelForCausalLM.from_pretrained("TenzinGayche/example_v1.0.2", torch_dtype=torch.float16).to("cuda")
+tokenizer = GemmaTokenizerFast.from_pretrained("TenzinGayche/ft_final")
+model = AutoModelForCausalLM.from_pretrained("TenzinGayche/ft_final", torch_dtype=torch.float16).to("cuda")
 
 model.config.sliding_window = 4096
 model.eval()