google

/

gemma-3n-E4B-it

like 734

Follow

Google 25.7k

First in order to avoid unknown mobilenetv5_300m_enc errors:
!pip uninstall -y timm
!pip install timm --upgrade

Then run the inference example of the model card and got: NotImplementedError: Cannot copy out of meta tensor; no data!
Full log:
The following generation flags are not valid and may be ignored: ['top_p', 'top_k']. Set TRANSFORMERS_VERBOSITY=info for more details.

NotImplementedError Traceback (most recent call last)
/tmp/ipython-input-1-875231982.py in <cell line: 0>()
35
36 with torch.inference_mode():
---> 37 generation = model.generate(**inputs, max_new_tokens=100, do_sample=False)
38 generation = generation[0][input_len:]
39

21 frames
/usr/local/lib/python3.11/dist-packages/transformers/models/gemma3n/modeling_gemma3n.py in scale_corrected_output(self, corrected)
1138 def scale_corrected_output(self, corrected: torch.Tensor) -> torch.Tensor:
1139 """Scales the provided 3D tensor of shape [batch_size, num_tokens, hidden_size]."""
-> 1140 return (corrected.type_as(self.correct_output_scale) * self.correct_output_scale).type_as(corrected)
1141
1142

NotImplementedError: Cannot copy out of meta tensor; no data!