facebookresearch/fairseq

Disparity with huggingface implementation when reproducing the fill_mask

Open

#1,399 创建于 2019年11月19日

在 GitHub 查看
 (8 评论) (0 反应) (0 负责人)Python (29,107 star) (6,224 fork)batch import
bughelp wanted

描述

I was not able to reproduce the fill mask provided here with the huggingface interface, wondering if they are using an outdated model (if a new one has been released) :)

贡献者指南

技术栈
pythonpytorch
领域
machine learningai
议题类型
bug
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
4
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
1-3 hours
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
stale
清晰度议题是否清楚说明期望改动、验收标准和下一步。
needs investigation
前置要求
fairseq basicsHuggingFace transformersfill mask task understanding
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
20
研究方向
Investigate the fill mask reproduction steps in fairseq and compare with HuggingFace's implementation. Check if the model checkpoint used by fairseq is outdated or if there are differences in tokenization or masking logic. Look at the fairseq documentation and any linked examples, then identify the specific disparities and suggest a fix or clarification.