Ctrl+K

4 contributors

ptx0

13000 steps: trained from ptx0/pseudo-journey, polynomial learning rate scheduler, batch size 3, text encoder, 8bit ADAM, ZERO PLW (no regularization data)

9135a79 almost 3 years ago

merges.txt

525 kB
13000 steps: trained from ptx0/pseudo-journey, polynomial learning rate scheduler, batch size 3, text encoder, 8bit ADAM, ZERO PLW (no regularization data) almost 3 years ago
special_tokens_map.json

460 Bytes
13000 steps: trained from ptx0/pseudo-journey, polynomial learning rate scheduler, batch size 3, text encoder, 8bit ADAM, ZERO PLW (no regularization data) almost 3 years ago
tokenizer_config.json

737 Bytes
13000 steps: trained from ptx0/pseudo-journey, polynomial learning rate scheduler, batch size 3, text encoder, 8bit ADAM, ZERO PLW (no regularization data) almost 3 years ago
vocab.json

1.06 MB
13000 steps: trained from ptx0/pseudo-journey, polynomial learning rate scheduler, batch size 3, text encoder, 8bit ADAM, ZERO PLW (no regularization data) almost 3 years ago