Upload generate_prompt.py with huggingface_hub

generate_prompt.py

@@ -99,9 +99,10 @@ for batch_idx in tqdm(range(begin, end, batch_size)):
         return_tensors="pt",
     )
     inputs = inputs.to(model.device)
-    print(inputs.shape)
+
     # Inference: Generation of the output
     generated_ids = model.generate(**inputs, max_new_tokens=128)
+    print(generated_ids.shape)
     generated_ids_trimmed = [
         out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
     ]