박정운

Hi, I'm trying to serve BERT-squad model on docker with **REST** 1. I export BERT-squad model with below code AND got the `export_model (saved_model.pb, variables, ... etc)` files ``` def...

I'm building on `x86_64` (and `Ubuntu 18.04`) I temporarily resolved it now. how to solve is below **Method 1.** rollback `Dockerfile` like [this](https://github.com/NVIDIA/DeepLearningExamples/blame/77292deab991afe83d7de26eb39108157abf1e91/TensorFlow2/LanguageModeling/ELECTRA/Dockerfile) **Method 2.** Use `docker buildx` command (Don't...

I find there are 2 parts in `Dockerfile` One is for ARM, Another is for x86. So I have to comment out upper chunk of [Dockerfile](https://github.com/NVIDIA/DeepLearningExamples/blob/eb3571096d13f04a71c802b005000f488a8f0139/TensorFlow2/LanguageModeling/ELECTRA/Dockerfile) and use from [here](https://github.com/NVIDIA/DeepLearningExamples/blob/eb3571096d13f04a71c802b005000f488a8f0139/TensorFlow2/LanguageModeling/ELECTRA/Dockerfile#L49)

> You only need to extract the generator or discriminator from the pretrained checkpoint for conversion. Typically the discriminator. Follow steps listed here to extract the individual parts. > >...

I found Why `keyerror` raised. Maybe some of your custom-dataset are shorter than 3 seconds (default `seg_dur` argument). Audio files that shorter than 3 seconds don't record to csv Check...

Hi, I encounter same problem. Here is my error log > [error_qwen2-7b.txt](https://github.com/user-attachments/files/16081450/error_qwen2-7b.txt) I use `docker container python:3.11 `, `pip install -r requirements.txt`, GPU drvier version: 535.104.05, CUDA Version: 12.2, NVIDIA...

When i use only 1 GPU, It works. But It doesn't work when I've used more than 2 GPUs.