How do I run glm4.6v on LM Studio 0.3.34? I'm getting the error "TypeError: TextConfig.init() missing 1 required positional argument: 'rope_theta'".

#1
by mimeng1990 - opened

How do I run glm4.6v on LM Studio 0.3.34? I'm getting the error "TypeError: TextConfig.init() missing 1 required positional argument: 'rope_theta'".

MLX Community org

LM Studio has mlx-vlm 0.3.7.
But get the same error with mlx-vlm 0.3.9 on the command-line

MLX Community org

When downloading the latest mlx-vlm from github, it gives

The tokenizer you are loading from 'mlx-community_GLM-4.6V-Flash-4bit' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the fix_mistral_regex=True flag when loading this tokenizer to fix this issue.

ValueError: Failed to process inputs with error: PreTrainedTokenizerFast._batch_encode_plus() got an unexpected keyword argument 'images'

When downloading the latest mlx-vlm from github, it gives

The tokenizer you are loading from 'mlx-community_GLM-4.6V-Flash-4bit' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the fix_mistral_regex=True flag when loading this tokenizer to fix this issue.

ValueError: Failed to process inputs with error: PreTrainedTokenizerFast._batch_encode_plus() got an unexpected keyword argument 'images'

try pip install git+https://github.com/huggingface/transformer.git

MLX Community org

Thank you @Timmy-web !

That solved the problem.
pip install git+https://github.com/huggingface/transformers.git

Sign up or log in to comment