git
ask
hub
Privacy
Terms
Sign in with GitHub
kimiyoung/transformer-xl
↗
Stars ·
3,704
Language ·
Python
License ·
Apache-2.0
Simplify and Visualize This Repo
Scan the safety of this repo
Self Host this repo
Check out more work of Developer: kimiyoung
Ask anything about this repo to start.
Using the Transformer-XL PyTorch implementation, how do I load the pre-trained weights and generate text conditioned on a long input passage?
How do I run the Transformer-XL TensorFlow training script on multiple GPUs for character-level language modeling, following the tf/ subdirectory README?
What is the segment-level recurrence mechanism in Transformer-XL and how does it differ from standard transformer self-attention? Walk me through the relevant code.
How do I adapt the Transformer-XL PyTorch code to fine-tune on a custom dataset of long documents?
What benchmark datasets and metrics does Transformer-XL report results on, and how do I reproduce those evaluations from this repository?
Full explanation on explaingit →
📎
Send
By chatting or signing in you agree to the
Terms
and chat-message logging (revocable in
History
).