Upload infer_qwen2_vl.py with huggingface_hub

infer_qwen2_vl.py

@@ -91,18 +91,30 @@ for batch_idx in tqdm(range(begin, end, batch_size)):
     inputs = inputs.to("cuda")
 
     # Inference: Generation of the output
-    generated_ids = model.generate(**inputs, max_new_tokens=8192)
-    generated_ids_trimmed = [
-        out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
-    ]
-    output_text = processor.batch_decode(
-        generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
-    )
+    ans = []
+    for x in range(len(inputs)):
+        print(f"Generating {x}th image")
+        generated_ids = model.generate(**x, max_new_tokens=8192)
+        generated_ids_trimmed = [
+            out_ids[len(in_ids) :] for in_ids, out_ids in zip(x.input_ids, generated_ids)
+        ]
+        output_text = processor.batch_decode(
+            generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=True
+        )
+        ans.append(output_text)
+
+    # generated_ids = model.generate(**inputs, max_new_tokens=8192)
+    # generated_ids_trimmed = [
+    #     out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
+    # ]
+    # output_text = processor.batch_decode(
+    #     generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
+    # )
     #ans.append(output_text)
     save_path = "output.json"
     counter = counter + 1
     if counter % 1 == 0:
         print(f"Saving data at iteration {idx + 1}")
-        write_json(save_path, data)
+        write_json(save_path, ans)