bug: `cortex run`: Error: `Error: Please delete model before downloading again bug`

[gabrielle-ong]

Cortex version

v1.0.0-141

Describe the Bug

Issue faced when running an already downloaded huggingface model author/model_id

> cortex-nightly run bartowski/Meta-Llama-3.1-8B-Instruct-GGUF
...
Selected: Meta-Llama-3.1-8B-Instruct-Q2_K.gguf
Model already downloaded: bartowski:Meta-Llama-3.1-8B-Instruct-GGUF:Meta-Llama-3.1-8B-Instruct-Q2_K.gguf
Error: Please delete the model before downloading again

Error: Model not found

Expected behaviour:

1. I expect it to run the downloaded model
2. I expected the model alias to be the huggingface path bartowski/Meta-Llama-3.1-8B-Instruct-GGUF

Screenshots / Logs

Mac:

What is your OS?

• [x] MacOS
• [ ] Windows
• [ ] Linux

What engine are you running?

• [X] cortex.llamacpp (default)
• [ ] cortex.tensorrt-llm (Nvidia GPUs)
• [ ] cortex.onnx (NPUs, DirectML)

[gabrielle-ong]

Retrying this with v172, redownloading a already downloaded HF model bartowski/Meta-Llama-3.1-8B-Instruct-GGUF Getting an uncaught error, but cortex chat successfully runs

Selected: Meta-Llama-3.1-8B-Instruct-Q2_K.gguf
Model already downloaded: bartowski:Meta-Llama-3.1-8B-Instruct-GGUF:Meta-Llama-3.1-8B-Instruct-Q2_K.gguf
libc++abi: terminating due to uncaught exception of type cpp::bitwizeshift::bad_result_access<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>>: error attempting to access value from result containing error
[1]    28174 abort      cortex-nightly run bartowski/Meta-Llama-3.1-8B-Instruct-GGUF

[gabrielle-ong]

Closing the original issue

• Create a new issue later