这里有个bug

[busishengui]

File "/data/renkl1/renkl/Stream-Omni/./stream_omni/eval/run_stream_omni.py", line 270, in
eval_model(args)
File "/data/renkl1/renkl/Stream-Omni/./stream_omni/eval/run_stream_omni.py", line 191, in eval_model
output_ids = model.generate(
^^^^^^^^^^^^^^^
File "/data/renkl1/env/anaconda3/envs/python3.12/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/data/renkl1/renkl/Stream-Omni/stream_omni/model/language_model/stream_omni_llama.py", line 1306, in generate
(inputs, position_ids, attention_mask, _, inputs_embeds, _, fake_inputs_embeds, bottom_audio_labels, inputs_embeds_proj) = self.prepare_inputs_labels_for_multimodal_audio(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/data/renkl1/renkl/Stream-Omni/stream_omni/model/stream_omni_arch.py", line 844, in prepare_inputs_labels_for_multimodal_audio
cur_input_embeds, cur_input_embeds_proj, cur_audio_logits = self.encode_audio(torch.cat(cur_input_ids_noim).unsqueeze(0), past_key_values)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/data/renkl1/renkl/Stream-Omni/stream_omni/model/stream_omni_arch.py", line 209, in encode_audio
audio_outputs = self.get_model()(
^^^^^^^^^^^^^^^^^
File "/data/renkl1/env/anaconda3/envs/python3.12/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/data/renkl1/env/anaconda3/envs/python3.12/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/data/renkl1/renkl/Stream-Omni/stream_omni/model/language_model/stream_omni_llama.py", line 459, in forward
next_decoder_cache = layer_outputs[2 if output_attentions else 1]
~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
IndexError: tuple index out of range

[wenxian-yang]

I also encountered it. Have you fixed this bug?