WARN Status Code: 500

[concretejungles]

Running a simple hf download Qwen/Qwen3-4B in colab, I keep getting infinite retries with:
WARN Status Code: 500

With RuntimeError: Data processing error: CAS service error : Reqwest Error: HTTP status server error (500 Internal Server Error), domain: ``https://cas-server.xethub.hf.co/reconstructions/a6f5dec111c34cd267ff4fd7889ef961237b30418d123d5b60b2c1fd3cbd3cc7 in the end.

Neither does download work locally.

Anyone else with a similar issue?

---

[FallingStar624]

Downloading cais/mmlu datasets, I also got 500 Status Code…

{“timestamp”:“2025-10-20T07:26:25.509409Z”,“level”:“WARN”,“fields”:{“message”:“Status Code: 500. Retrying…”,“request_id”:“01K80868M30G1GN7QQV2VYSXHF”},“filename”:“/home/runner/work/xet-core/xet-core/cas_client/src/http_client.rs”,“line_number”:236}
{“timestamp”:“2025-10-20T07:26:25.509463Z”,“level”:“WARN”,“fields”:{“message”:“Retry attempt #0. Sleeping 879.55434ms before the next attempt”},“filename”:“/root/.cargo/registry/src/index.crates.io-1949cf8c6b5b557f/reqwest-retry-0.7.0/src/middleware.rs”,“line_number”:171}

[drrobot333]

Hi, I have same problem..

2025-10-20T07:38:03.814777Z WARN Status Code: 500. Retrying…, request_id: “01K808VJJ5TG7VWFE823WB7E9B”
at /home/runner/work/xet-core/xet-core/cas_client/src/http_client.rs:227

2025-10-20T07:38:03.814851Z WARN Retry attempt #0. Sleeping 1.198937597s before the next attempt
at /root/.cargo/registry/src/index.crates.io-1949cf8c6b5b557f/reqwest-retry-0.7.0/src/middleware.rs:171

======================================

However, simply downloading llm models using huggingface-cli download {model_name} works perfectly.

[iamnotwhale]

huggingface-cli download {model_name} does not work for me

2025-10-20T07:47:18.579473Z WARN Status Code: 500. Retrying…, request_id: “01K809CGAP7ZB4QJ1Y3S3J636A” | 0.00/99.6M [00:00<?, ?B/s]
at /home/runner/work/xet-core/xet-core/cas_client/src/http_client.rs:220

2025-10-20T07:47:18.579520Z WARN Retry attempt #0. Sleeping 955.2374ms before the next attempt | 0.00/11.4M [00:00<?, ?B/s]
at /root/.cargo/registry/src/index.crates.io-1949cf8c6b5b557f/reqwest-retry-0.7.0/src/middleware.rs:171

2025-10-20T07:47:18.587662Z WARN Status Code: 500. Retrying…, request_id: “01K809CGAWZTSR5S63S4461HM6”
at /home/runner/work/xet-core/xet-core/cas_client/src/http_client.rs:220

2025-10-20T07:47:18.587702Z WARN Retry attempt #0. Sleeping 2.634600073s before the next attempt
at /root/.cargo/registry/src/index.crates.io-1949cf8c6b5b557f/reqwest-retry-0.7.0/src/middleware.rs:171

[drrobot333]

I solved the issue by disabling xet, like this:

export HF_HUB_DISABLE_XET=1

After setting this environment variable, the download worked perfectly.

[charpef8]

Thank you, you saved me. What is this Environment variable supposed to do ?

[John6666]

@jsulz Xet related issue?

[drrobot333]

It disables Hugging Face’s new xet-based large file backend and falls back to the old HTTP download method.

[mantou-cloud]

@drrobot333

export HF_HUB_DISABLE_XET=1

It doesn’t work for me…

[John6666]

idk related or not. seems AWS is now in trouble. (of course worldwide)

[sciciliano]

Disabling the XET backend doesn’t seem to work, I’m getting the exact same error as before –>

RuntimeError: Data processing error: CAS service error : Reqwest Error: HTTP status server error (500 Internal Server Error)

I don’t think the issue is solved yet, alas

[scanasca10]

This has work for me

uv pip install --system ‘huggingface_hub[cli]’; \
uv pip uninstall --system hf-xet; \
huggingface-cli download \

[John6666]

Other Hub features also appear to be unstable due to the AWS outage.

Hugging Face status