Getting 401 Unauthorized while downloading models via Tabby

Beginners
1

I am facing an issue while downloading the models via Tabby.ai. Earlier it was working fine but, since yesterday evening it has stopped working.

root@ip-172-31-10-103:/home/ubuntu/tabby/tabby/target/debug# ./tabby serve --model Qwen2.5-Coder-14B --port 8723 --host 0.0.0.0
2025-01-31T09:36:18.486111Z WARN tabby::serve: crates/tabby/src/serve.rs:378: Overriding completion model from config.toml. The overriding behavior might surprise you. Consider setting the model in config.toml directly.
Writing to new file.
File exists. Resuming.
File exists. Resuming.
The application panicked (crashed).
Message: Failed to fetch model ‘Qwen2.5-Coder-14B’ due to ‘Fetching ‘https://huggingface.co/ikw/Qwen2.5-Coder-14B-GGUF/resolve/main/qwen2.5-coder-14b-q8_0.gguf’ failed: Server returned HTTP status client error (401 Unauthorized) for url (https://huggingface.co/ikw/Qwen2.5-Coder-14B-GGUF/resolve/main/qwen2.5-coder-14b-q8_0.gguf) HTTP status’
Location: /home/azureuser/tabby/tabby/crates/tabby-download/src/lib.rs:210

2 Likes
2

Same here:

Σ ~ tabby serve --device metal --model StarCoder-1B --chat-model Qwen2-1.5B-Instruct
Writing to new file.
File exists. Resuming.
File exists. Resuming.
The application panicked (crashed).
Message:  Failed to fetch model 'StarCoder-1B' due to 'Fetching 'https://huggingface.co/TabbyML/models/resolve/main/starcoderbase-1B.Q8_0.gguf' failed: Server returned HTTP status client error (401 Unauthorized) for url (https://huggingface.co/TabbyML/models/resolve/main/starcoderbase-1B.Q8_0.gguf) HTTP status'
Location: /Users/runner/work/tabby/tabby/crates/tabby-download/src/lib.rs:210

Backtrace omitted. Run with RUST_BACKTRACE=1 environment variable to display it.
Run with RUST_BACKTRACE=full to include source snippets.

I was thinking that maybe the tabby-client configuration could need some kind of token but I didn’t find anything related with this, so…

1 Like
3

I’ve updated to the last tabbyml version using brew and looks much better:

Writing to new file.
🎯 Transferring https://huggingface.co/TabbyML/models/resolve/main/starcoderbase-1B.Q8_0.gguf
⠉  00:00:44 ▕███▊                ▏ 239.28 MiB/1.23 GiB  5.69 MiB/s  ETA 3m.

So I think AzilenTech, you just need to update the app

1 Like