Junyang Lin
Junyang Lin
@AK391 just helped me solve the problem by setting `cache_examples=False`. I think the problem should come from this place and you can check that part of the code.
> I'd suggest using checkboxes, so we can track our progress over time. Could probably also just use ~strike~ to cross off completed items Yeah for the readme I'll make...
Any code for reproduction or a colab notebook?
which size and which finetuning codebase are you using
torch_dtype='auto'. Check the latest readme
no plan temporarily.
this is the problem of autogptq. gotta report this to them
never had experience in training with tgw. try to use ours, llama factory, or axolotl. we don't advise tgw for training
Try our provided one or use Axolotl or LLaMA-Factory
https://qwen.readthedocs.io/zh-cn/latest/inference/chat.html check this doc. your model input can be a list of text