Giter Club home page Giter Club logo

Comments (9)

lixumin-zai avatar lixumin-zai commented on August 11, 2024

看下bert的实现代码吧,看了就知道这些参数信息了,虽然本人也还没认真看过bert的源码。

from ttt.

chaohen avatar chaohen commented on August 11, 2024

看下bert的实现代码吧,看了就知道这些参数信息了,虽然本人也还没认真看过bert的源码。

你好请问这个模型有成功运行吗? 求一下运行方法

from ttt.

lixumin-zai avatar lixumin-zai commented on August 11, 2024

from ttt.

fujunying2018 avatar fujunying2018 commented on August 11, 2024

您好,您在下面的代码模块儿做了哪些处理呢,可以举个例子吗
bert_ckpt= torch.load(args.bert_path)
bert_args = bert_ckpt['args']

from ttt.

li-aolong avatar li-aolong commented on August 11, 2024

您好,您在下面的代码模块儿做了哪些处理呢,可以举个例子吗
bert_ckpt= torch.load(args.bert_path)
bert_args = bert_ckpt['args']

@lixumin-zai

from ttt.

fujunying2018 avatar fujunying2018 commented on August 11, 2024

main.py文件里开始训练的时候需要加载模型,模型内容包括了训练时的参数'args',但是初次训练的话并没有这个参数,请问该如何获得?

bert_ckpt= torch.load(args.bert_path)
bert_args = bert_ckpt['args']

而且,在加载模型的时候需要bert_args.embed_dim这些参数,代码里也没有找到,想问一下是否能够开源一个已经训练好的模型?

bert_model = BERTLM(device, bert_vocab, bert_args.embed_dim, bert_args.ff_embed_dim, bert_args.num_heads, \
                                     bert_args.dropout, bert_args.layers, bert_args.approx)

另外,模型训练的超参数是和train.sh里一致的吗?

您好,您这块儿运行起来了吗?如果运行起来是否可以分享下这块儿的修改代码

from ttt.

li-aolong avatar li-aolong commented on August 11, 2024

@fujunying2018 没跑起来,最近也没看了,上边有人说成功了,我给你@了

from ttt.

fujunying2018 avatar fujunying2018 commented on August 11, 2024

好的,谢谢

from ttt.

lipiji avatar lipiji commented on August 11, 2024

Will release it before 31 Dec.

from ttt.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.