Lambda14

Try to run DeepSeek-Coder-V2-Lite with 16G GPU memory and get Out of memory error

6

Hello, I'm trying to run tabby with model DeepSeek-Coder-V2-Lite on windows using the command: .\tabby.exe serve --model DeepSeek-Coder-V2-Lite --chat-model Qwen2-1.5B-Instruct --device cuda and I get memory allocation error: allocating 15712.47...

`values()` returns wrong results when used with list values (JSONField)

5

If you create model with list in attribute `MockSet(MockModel(list_attr=pytest.pydict()))` then tries to ``` self.model.objects.filter(id=_id).values("list_attr").first() > {'list_attr': 'nAvOpyEVAoNGnVZQUqLU'} ``` if call attribute directly `self.model.objects.filter(id=_id).first().list_attr` it returns full list `['nAvOpyEVAoNGnVZQUqLU', '[email protected]', 3350,...