facebookresearch/fairseq

Providing Models in SafeTensors format

Open

#5,257 创建于 2023年7月16日

在 GitHub 查看
 (0 评论) (1 反应) (0 负责人)Python (29,107 star) (6,224 fork)batch import
enhancementhelp wantedneeds triage

描述

Hi,

We are currently utilizing models in our project stored in pickle format. However, after exploring the advantages of SafeTensors in terms of improved security we believe that it will provide us with an extra layer of security and protection against potential vulnerabilities. model link

We wish to inquire about the plans or timeline, if any, regarding the update of models from pickle to SafeTensors:

  • Are there any plans to update the models to SafeTensors?
  • If yes, is there a projected timeline for this migration?

贡献者指南

技术栈
pythonpytorch
领域
machine learningsecurity
议题类型
feature
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。
2
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。
under 1 hour
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。
needs maintainer response
清晰度议题是否清楚说明期望改动、验收标准和下一步。
clear
前置要求
PythonPyTorchmodel serialization
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
This issue asks about converting models from pickle to SafeTensors. To address it, first check the repository for any existing SafeTensors conversion scripts or discussions. Then explore the SafeTensors library documentation for conversion steps. The linked model file (https://download.pytorch.org/torchaudio/models/wav2vec2 fairseq base ls960 asr ls960.pth) can be used as a test case. Provide a recommendation on whether conversion is feasible and a rough timeline.
Providing Models in SafeTensors format · facebookresearch/fairseq#5257 | Good First Issue