Ranran

https://github.com/ShulinCao/OpenNRE-PyTorch/blob/master/networks/selector.py#L70 You use dropout after sen_matrix in the training stage, and not use it in the test stage. I think the nuance of dropout should be manipulated by model.eval(), rather...

### Author Pages My page (Ranran Haoran Zhang): https://aclanthology.org/people/r/ranran-haoran-zhang/ Some of my old papers are on Haoran Zhang's page (my old name, which is conflated with others): https://aclanthology.org/people/h/haoran-zhang/ ### Type...

Besides NLI, I am also interested in the original label of the correct pairs, especially for the relation extraction task. As DNC contains 574 relations and 354 templates, it is...

[Feature Request]: Batched Async Prediction

2

Hi, The current scikit-llm is implemented in a synchronous way - the prompts are sent to the api one-by-one. This is not ideal when we have a large dataset and...

I tried to finetune GoLLIE-7b on crossner-ai. ``` bash bash_scripts/generate_data.sh bash bash_scripts/GoLLIE-7B_CodeLLaMA.sh ``` I only trimmed the yaml to below: ``` train_tasks: - crossner.crossner_ai validation_tasks: - crossner.crossner_ai test_tasks: - crossner.crossner_ai...