Pickle error when downloading DeepSeek model

[andrewsykim]

System Info

I'm consistently running into this pickle error when trying to run DeepSeek R1 models (both R1 and R1-0528):

Can't pickle <class 'transformers_modules.deepseek-ai.DeepSeek-R1-0528.4236a6af538feda4548eca9ab308586007567f52.configuration_deepseek.DeepseekV3Config'>:
it's not the same object as transformers_modules.deepseek-ai.DeepSeek-R1-0528.4236a6af538feda4548eca9ab308586007567f52.configuration_deepseek.DeepseekV3Config"

Who can help?

No response

Information

• The official example scripts
• My own modified scripts

Tasks

• An officially supported task in the examples folder (such as GLUE/SQuAD, ...)
• My own task or dataset (give details below)

Reproduction

Deploy DeepSeek R1 using vLLM

Expected behavior

No pickle error

[andrewsykim]

I suspect something changed between the uploaded configuration_deepseek.py file on hugging face and the one in the repo.

[Rocketknight1]

Hi @andrewsykim, can you give us some code that reproduces the issue?