SmolVLM2: Bringing Video Understanding to Every Device

when run this script: python -m mlx_vlm.generate --model mlx-community/SmolVLM2-500M-Video-Instruct-mlx --image https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg --prompt "Can you describe this image?"

====================================== test errror: Files: ['https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg']

Prompt: <|im_start|>User:Can you describe this image? Assistant: Traceback (most recent call last): File "", line 198, in _run_module_as_main File "", line 88, in _run_code File "/opt/homebrew/Caskroom/miniconda/base/envs/playwright/lib/python3.12/site-packages/mlx_vlm/generate.py", line 156, in main() File "/opt/homebrew/Caskroom/miniconda/base/envs/playwright/lib/python3.12/site-packages/mlx_vlm/generate.py", line 141, in main output = generate( ^^^^^^^^^ File "/opt/homebrew/Caskroom/miniconda/base/envs/playwright/lib/python3.12/site-packages/mlx_vlm/utils.py", line 1115, in generate for response in stream_generate(model, processor, prompt, image, **kwargs): ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/opt/homebrew/Caskroom/miniconda/base/envs/playwright/lib/python3.12/site-packages/mlx_vlm/utils.py", line 1016, in stream_generate inputs = prepare_inputs( ^^^^^^^^^^^^^^^ File "/opt/homebrew/Caskroom/miniconda/base/envs/playwright/lib/python3.12/site-packages/mlx_vlm/utils.py", line 806, in prepare_inputs processor.tokenizer.pad_token = processor.tokenizer.eos_token ^^^^^^^^^^^^^^^^^^^ File "/opt/homebrew/Caskroom/miniconda/base/envs/playwright/lib/python3.12/site-packages/transformers/tokenization_utils_base.py", line 1108, in getattr raise AttributeError(f"{self.class.name} has no attribute {key}") AttributeError: GPT2TokenizerFast has no attribute tokenizer. Did you mean: '_tokenizer'?