Issues

• Missing a negative sign on the exponent for RoPE

  labmlai/annotated_deep_learning_paper_implementations#313 · Filter by author yijing-sie opened on Sep 10, 2026

• The number of channels is weird

  labmlai/annotated_deep_learning_paper_implementations#296 · Filter by author optstats opened on Jan 31, 2026

• Is there an option to donate to this project?

  labmlai/annotated_deep_learning_paper_implementations#294 · Filter by author ekagra-ranjan opened on Jan 20, 2026

• Minor corrections in documentation for Nucleus Sampling implementation

  labmlai/annotated_deep_learning_paper_implementations#293 · Filter by author chiamerica opened on Jan 3, 2026

• labml.configs 中缺少定义FloatDynamicHyperParam, IntDynamicHyperParam，我无法从labml.configs中导入，我去查看了这个文件，里面缺少定义

  labmlai/annotated_deep_learning_paper_implementations#291 · Filter by author gujude1-svg opened on Nov 6, 2025

• in TransformerXLLayer code snippet will face with issues

  labmlai/annotated_deep_learning_paper_implementations#285 · Filter by author alokamgnaneswarasai opened on Mar 3, 2025

• Why is Center Crop used for skip connections instead of Padding in U-Net?

  labmlai/annotated_deep_learning_paper_implementations#281 · Filter by author dyedd opened on Jan 5, 2025

• How to Contribute to This Repository

  labmlai/annotated_deep_learning_paper_implementations#275 · Filter by author terancejiang opened on Sep 15, 2024
  8

• Unet error in DDPM

  labmlai/annotated_deep_learning_paper_implementations#270 · Filter by author TwinkleStarst opened on Aug 14, 2024
  4

• Request for Implementation of Mamba Paper

  labmlai/annotated_deep_learning_paper_implementations#261 · Filter by author huyiwen opened on Jul 2, 2024

• How to use my own database for training and evaluating Retro for Question-Answering?

  labmlai/annotated_deep_learning_paper_implementations#260 · Filter by author Zahin112 opened on Jun 27, 2024
  2

• "pip install labml-nn" generated errors. How to resolve it and complete the installation?

  labmlai/annotated_deep_learning_paper_implementations#247 · Filter by author jxwanguab opened on Mar 14, 2024

• ppo code running error

  labmlai/annotated_deep_learning_paper_implementations#245 · Filter by author cxw-droid opened on Feb 28, 2024
  2

• DDPM interpolation formula error

  labmlai/annotated_deep_learning_paper_implementations#238 · Filter by author jjjuuuun opened on Jan 25, 2024

• Question about gatv2 code

  labmlai/annotated_deep_learning_paper_implementations#228 · Filter by author XiaokangORCA opened on Nov 20, 2023
  1

• Request for Paper Implementation - Neural Operators

  paper implementation
  labmlai/annotated_deep_learning_paper_implementations#219 · Filter by author Robertboy18 opened on Oct 26, 2023
  1

• Is there some errors in transformers mha.py

  labmlai/annotated_deep_learning_paper_implementations#216 · Filter by author lqzzy opened on Sep 28, 2023
  1

• Stride = 2 only for the first block of the entire ResNet

  labmlai/annotated_deep_learning_paper_implementations#205 · Filter by author PavelShtykov opened on Aug 16, 2023

• Small issue in nucleus sampling explanation + implementation

  labmlai/annotated_deep_learning_paper_implementations#203 · Filter by author ascher8 opened on Aug 10, 2023

• q,k,v have different shape but torch.stack works?

  labmlai/annotated_deep_learning_paper_implementations#202 · Filter by author junsukha opened on Aug 8, 2023

• Training code or references for training the latent diffusion model on a custom dataset

  paper implementation
  labmlai/annotated_deep_learning_paper_implementations#195 · Filter by author mitchell-cheng opened on Jul 8, 2023
  3

• Bug in Transformer-XL shift method

  bug
  labmlai/annotated_deep_learning_paper_implementations#185 · Filter by author Bearnardd opened on May 16, 2023
  1

• MultiHeadAttention parameter setting

  improvement
  labmlai/annotated_deep_learning_paper_implementations#180 · Filter by author LXXiaogege opened on Apr 30, 2023
  2

  

• The classifier-free guidance of diffusion models is wrong.

  bug
  labmlai/annotated_deep_learning_paper_implementations#177 · Filter by author luowyang opened on Apr 9, 2023
  

• is the kld not in ppo total loss?

  question
  labmlai/annotated_deep_learning_paper_implementations#171 · Filter by author pandaupc opened on Mar 5, 2023
  1