Mac Dimension out of range

[skqszy123]

MAC mini M2 os 15.3.1 (24D70) Python 3.13.2 pip 25.0.1 Requirement already satisfied: torch in /opt/homebrew/lib/python3.13/site-packages (2.6.0) Requirement already satisfied: torchvision in /opt/homebrew/lib/python3.13/site-packages (0.21.0) Requirement already satisfied: torchaudio in /opt/homebrew/lib/python3.13/site-packages (2.6.0)

File "/Users/haloai01/Downloads/qwenvl.py", line 55, in generated_ids = model.generate(**inputs, max_new_tokens=128) File "/opt/homebrew/lib/python3.13/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context return func(*args, **kwargs) File "/opt/homebrew/lib/python3.13/site-packages/transformers/generation/utils.py", line 2228, in generate result = self._sample( input_ids, ...<5 lines>... **model_kwargs, ) File "/opt/homebrew/lib/python3.13/site-packages/transformers/generation/utils.py", line 3211, in _sample outputs = self(**model_inputs, return_dict=True) File "/opt/homebrew/lib/python3.13/site-packages/torch/nn/modules/module.py", line 1739, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^ File "/opt/homebrew/lib/python3.13/site-packages/torch/nn/modules/module.py", line 1750, in _call_impl return forward_call(*args, **kwargs) File "/opt/homebrew/lib/python3.13/site-packages/transformers/models/qwen2_5_vl/modeling_qwen2_5_vl.py", line 1740, in forward image_embeds = self.visual(pixel_values, grid_thw=image_grid_thw) File "/opt/homebrew/lib/python3.13/site-packages/torch/nn/modules/module.py", line 1739, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^ File "/opt/homebrew/lib/python3.13/site-packages/torch/nn/modules/module.py", line 1750, in _call_impl return forward_call(*args, **kwargs) File "/opt/homebrew/lib/python3.13/site-packages/transformers/models/qwen2_5_vl/modeling_qwen2_5_vl.py", line 501, in forward hidden_states = blk( hidden_states, cu_seqlens=cu_seqlens_now, rotary_pos_emb=rotary_pos_emb, ) File "/opt/homebrew/lib/python3.13/site-packages/torch/nn/modules/module.py", line 1739, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^ File "/opt/homebrew/lib/python3.13/site-packages/torch/nn/modules/module.py", line 1750, in _call_impl return forward_call(*args, **kwargs) File "/opt/homebrew/lib/python3.13/site-packages/transformers/models/qwen2_5_vl/modeling_qwen2_5_vl.py", line 297, in forward hidden_states = hidden_states + self.attn( ~~~~~~~~~^ self.norm1(hidden_states), ^^^^^^^^^^^^^^^^^^^^^^^^^^ cu_seqlens=cu_seqlens, ^^^^^^^^^^^^^^^^^^^^^^ rotary_pos_emb=rotary_pos_emb, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ) ^ File "/opt/homebrew/lib/python3.13/site-packages/torch/nn/modules/module.py", line 1739, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^ File "/opt/homebrew/lib/python3.13/site-packages/torch/nn/modules/module.py", line 1750, in _call_impl return forward_call(*args, **kwargs) File "/opt/homebrew/lib/python3.13/site-packages/transformers/models/qwen2_5_vl/modeling_qwen2_5_vl.py", line 272, in forward attn_output = F.scaled_dot_product_attention(q, k, v, attention_mask, dropout_p=0.0) IndexError: Dimension out of range (expected to be in range of [-3, 2], but got 3)