Add log to see why HF is hanging

app.py

@@ -69,6 +69,7 @@ def generate_text(prompt, extra=False, top_k=100, top_p=0.95, temperature=0.85,
     samples = []
     try:
         for i in range(1):
+            print(f"Generating sample {i+1}")
             outputs = model.generate(**inputs, max_length=256, do_sample=True, top_k=top_k, top_p=top_p, temperature=temperature, num_return_sequences=4, pad_token_id=tokenizer.eos_token_id)
             for output in outputs:
                 sample = tokenizer.decode(output, skip_special_tokens=True)