Repository Issue Activity (beta)

#301 Mc_Paper

#296 The number of channels is weird

#294 Is there an option to donate to this project?

#293 Minor corrections in documentation for Nucleus Sampling implementation

#292 💡 Bounty Platform for Annotated Deep Learning Papers

#291 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

#245 ppo code running error

#270 Unet error in DDPM

#288 安装不了labml_helpers包

#262 mha.py array shapes

#246 question about RotaryPEMultiHeadAttention: rotary_percentage

#282 Attention takes softmax over wrong dimension

#263 LORA

#257 Chinese Translation

#254 connection timed out

#275 How to Contribute to This Repository

#241 Wrong Image Scale in DDPM

#253 Question about RoPE code

#285 in TransformerXLLayer code snippet will face with issues

#283 How to run model on multiple GPUs?

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

#219 Request for Paper Implementation - Neural Operators

#261 Request for Implementation of Mamba Paper

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

#135 RETRO: RuntimeError: stack expects each tensor to be equal size, but got [2, 32] at entry 0 and [1, 32] at entry 29