Runpod•3w ago

Update Transformers Library

Hi, I am trying to run Qwen/Qwen3-Embedding-8B via serverless endpoints. 1. I select quick deploy, Infinity Vector Embeddings. 2. Set Qwen/Qwen3-Embedding-8B as the model. 3. Batch size 32, data type auto. 4. Torch backend 5. Endpoint type: queue 6. 24 Gb GPU selected Inspecting worker logs:

ValueError: The checkpoint you are trying to load has model type `qwen3` 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 This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

ValueError: The checkpoint you are trying to load has model type `qwen3` 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 This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

This is a known issue as per HF: https://huggingface.co/Qwen/Qwen3-Embedding-8B#usage I need to update the Transformers library. How can I do that? Any guidance is much appreciated.

Qwen/Qwen3-Embedding-8B · Hugging Face

2 Replies

matt•3w ago

same for gpt-oss, the docker images need to be udpated

ziggyOP•3w ago

Ill have a go creating my own docker image to run

Gaming

Programming

Update Transformers Library

Did you find this page helpful?