Knover
Knover copied to clipboard
Large-scale open domain KNOwledge grounded conVERsation system based on PaddlePaddle
1) I download the 24L model, and run the finetune script `bash ./scripts/local/job.sh ./projects/PLATO-2/finetune/24L_train.conf`. I got nan for my loss at the very beginning of the fine-tuning. Am I missing...
Add some usefule scripts. - [x] evaluation - [x] self-chat
源码有开源吗
Hello Does this github include the code for the Speech Disfluency Simulator and Phoneme-level Simulator used in TOD-DA?
您好,我看了issue #24,尝试在24L的plato-2上使用persona定制,修改代码如下: https://github.com/PaddlePaddle/Knover/blob/9d0db786dca9c575b40eb5776c6620bbd6657070/knover/scripts/interact.py#L84 改成: ```python personas = ["your persona: i have three cats.", "your persona: i am 20 years old.", "your persona: i like eggs."] example = Example(src=" [SEP] ".join(personas...
Hello, Can you suggest how to get the perplexity of a target response using your model? What is the score in the [prediction](https://github.com/PaddlePaddle/Knover/blob/9d0db786dca9c575b40eb5776c6620bbd6657070/knover/scripts/infer.py#L87) about? Thanks!
感谢您开源的工作。如果手上没有大规模的训练数据,而又想利用已有模型的知识,是否能利用hugging face上transformer模型做微调?