can't run on vllm
The checkpoint you are trying to load has model type deepseek_vl_v2 but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.
I've run into the same issue, but my transformers were already updated. Have no clue.
Any solutions? Thanks you guys.
I have the same question。
ValueError: The checkpoint you are trying to load has model type deepseek_vl_v2 but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.
Check this out: https://huggingface.co/deepseek-ai/deepseek-vl2/discussions/3
For more details, you might look at https://docs.vllm.ai/en/latest/getting_started/examples/vision_language_multi_image.html