abhinavv3's picture
Repo before implementing concepts of the paper memorizing transformer
f6d6286
raw
history blame
199 Bytes
--extra-index-url https://download.pytorch.org/whl/cu121
safetensors==0.5.3
tiktoken==0.9.0
tokenizers==0.21.1
transformers==4.50.1
tqdm==4.67.1
requests==2.32.3
numpy<1.27,>=1.22
torch==2.3.1+cu121