Closed 123109 closed 10 months ago
不就是继续finetune就可以吗,在A模型上继续训练就行,如果觉得效果有偏,加点之前的样本。
卧槽,大佬回复这么快……是这个吗?fine-tune 使用transformers(旧称pytorch-pretrained-BERT)的examples/language-modeling/run_language_modeling.py处理。
是的,继续run,就是fine-tune
现在的问题,找不到run_language_modeling.py这个脚本……是不是要到commit记录里面去找?
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.(由于长期不活动,机器人自动关闭此问题,如果需要欢迎提问)