mint
mint copied to clipboard
dpressel
MinT: Minimal Transformer Library and Tutorials
Results
2
mint issues
Sort by
recently updated
recently updated
newest added
Add support for [OPT](https://arxiv.org/pdf/2205.01068.pdf). It is: - a decoder-only model with learned-positional embeddings up to 2k - same checkpoint structure as BART without encoder - GPT2 byte-level tokenizer with a...
A really great library! Thank you very much for the author's careful writing, very careful, from zero to one to achieve each powerful mainstream algorithm! Next， Can you implement a...
