Coder Social home page Coder Social logo

微调internXC2报错 about vl-rlhf HOT 9 OPEN

yuzeng0-0 avatar yuzeng0-0 commented on August 25, 2024
微调internXC2报错

from vl-rlhf.

Comments (9)

TideDra avatar TideDra commented on August 25, 2024 1

我们的实现方法加入了单独的image token标记图片位置,这在原模型中是没有的。您需要在模型的config.py文件中添加"image_token_index":92544

from vl-rlhf.

TideDra avatar TideDra commented on August 25, 2024 1

方便展示一下internXC2模型的config.py文件吗

可以参考我们放出的checkpoint: https://huggingface.co/TideDra/internlm-xcomposer2-vl-7b-DPO/blob/main/config.json

from vl-rlhf.

yuzeng0-0 avatar yuzeng0-0 commented on August 25, 2024 1

internXC2 的DPO代码还是跑不起来,您确定repo里是最新版本的代码吗?是不是repo是之前的版本导致有些bug没有修复

from vl-rlhf.

yuzeng0-0 avatar yuzeng0-0 commented on August 25, 2024

感谢

from vl-rlhf.

yuzeng0-0 avatar yuzeng0-0 commented on August 25, 2024

File "/cache/zy/VL-RLHF/src/vlrlhf/models/InternLMXC2/init.py", line 87, in _merge_input_ids_with_image_features
raise ValueError(
ValueError: The input provided to the model are wrong. The number of image tokens is 2 while the number of image given to the model is 2. This prevents correct indexing and breaks batch generation.这个怎么解决

from vl-rlhf.

yuzeng0-0 avatar yuzeng0-0 commented on August 25, 2024

File "/cache/zy/VL-RLHF/src/vlrlhf/models/InternLMXC2/init.py", line 87, in _merge_input_ids_with_image_features raise ValueError( ValueError: The input provided to the model are wrong. The number of image tokens is 2 while the number of image given to the model is 2. This prevents correct indexing and breaks batch generation.这个怎么解决
if image_to_overwrite.sum() != image_features.shape[:-1].numel():条件判断raise ValueError

from vl-rlhf.

TideDra avatar TideDra commented on August 25, 2024

我们统一用<image>作为image token,请检查下输入文本中image token的总数量与输入图片的总数量是否一致

from vl-rlhf.

yuzeng0-0 avatar yuzeng0-0 commented on August 25, 2024

我们统一用<image>作为image token,请检查下输入文本中image token的总数量与输入图片的总数量是否一致这个是没问题的。
我猜测是padding的问题,internXC2的pad_token_id是2,对应embedding为零向量,在执行final_embedding[image_to_overwrite] = image_features.contiguous().reshape(-1, embed_dim).to(target_device)的时候报错

from vl-rlhf.

yuzeng0-0 avatar yuzeng0-0 commented on August 25, 2024

方便展示一下internXC2模型的config.py文件吗

from vl-rlhf.

Related Issues (12)

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.