Invalid model_id for J-350M and T5P-220M

[praktiskt]

Describe the bug

Unable to run some of the models available on TabbyML huggingface.

Reproducible examples:

# TabbyML/J-350M fails
docker run tabbyml/tabby:0.5.5 serve --model TabbyML/J-350M

# TabbyML/T5P-220M fails
docker run tabbyml/tabby:0.5.5 serve --model TabbyML/T5P-220M

# TabbyML/StarCoder-1B works just fine
docker run tabbyml/tabby:0.5.5 serve --model TabbyML/StarCoder-1B

Information about your version

Tabby 0.5.5, using the docker-container tabbyml/tabby:0.5.5.

Information about your GPU

No GPU, just CPU.

Additional context

Setting RUST_BACKTRACE=1 yields the following stacktrace for T5P-220M. J-350M yields an identical error.

thread 'main' panicked at crates/tabby-common/src/registry.rs:72:32:
Invalid model_id <TabbyML/T5P-220M>
stack backtrace:
   0: rust_begin_unwind
             at ./rustc/cc66ad468955717ab92600c770da8c1601a4ff33/library/std/src/panicking.rs:595:5
   1: core::panicking::panic_fmt
             at ./rustc/cc66ad468955717ab92600c770da8c1601a4ff33/library/core/src/panicking.rs:67:14
   2: tabby_common::registry::ModelRegistry::get_model_info
   3: tabby_download::download_model::{{closure}}
   4: tabby::serve::main::{{closure}}
   5: tokio::runtime::park::CachedParkThread::block_on
   6: tokio::runtime::context::runtime::enter_runtime
   7: tokio::runtime::runtime::Runtime::block_on
   8: tabby::main

[wsxiaoys]

Hey - since 0.4.0, we removed T5P-220M / J-350M from supported model list: https://tabby.tabbyml.com/docs/models/

If you're interested in using a customized model in tabby, please refer the How can I convert my own model for use with Tabby? in https://tabby.tabbyml.com/docs/faq

[praktiskt]

Gotcha. Might make sense to remove the models from Huggingface if they are no longer supported (or flag them as such in their respective READMEs).

Closing since there's nothing else to be done. Thanks for the swift response 👍