Update app.py

app.py

@@ -15,6 +15,7 @@ def generate_text(prompt, temperature, top_p, top_k, repetition_penalty, max_len
     # Generate text using the model
     generator.model.cuda()
     generator.device = torch.device("cuda")
+    generator.tokenizer.eos_token = "<|im_end|>"
     prompt = f"<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n"
     outputs = generator(
         prompt,