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

labmlai / annotated_deep_learning_paper_implementations

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

https://nn.labml.ai

MIT License

54.54k stars 5.63k forks source link

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

Open Zahin112 opened 3 months ago

Zahin112 commented 3 months ago

What is the main purpose or outcome of this training? is it only for text completion? How do I finetune it for Question-Answering or any other downstream task?

I want to use my dataset in the training. How do I do it and which format the dataset needs to be?

Is there script to evaluate the model reproducing the results of the paper?

vpj commented 3 months ago

Which model are you referring to?

Zahin112 commented 3 months ago

Sorry I forgot to mention. I was referring to Retro.