2 contributors

History: 12 commits

pszemraj

clean up

9a08632 over 2 years ago

.gitattributes

1.17 kB

initial commit over 2 years ago
.gitignore

13 Bytes

update ckpt with 6ish epochs of training with 1024 TOKENS as max output over 2 years ago
README.md

13.1 kB

clean up over 2 years ago
config.json

1.14 kB

update ckpt with 6ish epochs of training with 1024 TOKENS as max output over 2 years ago
latest

14 Bytes

update ckpt with 6ish epochs of training with 1024 TOKENS as max output over 2 years ago
long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP4-ft2-booksum_training_metadata.json

3.17 kB

update ckpt with 6ish epochs of training with 1024 TOKENS as max output over 2 years ago
longt5-tglobal-large-pubmed-3k-booksum-8192-V4-ft2-booksum_training_metadata.json

3.16 kB

Upload longt5-tglobal-large-pubmed-3k-booksum-8192-V4-ft2-booksum_training_metadata.json over 2 years ago
pytorch_model.bin
Detected Pickle imports (3)
- "torch.FloatStorage",
- "collections.OrderedDict",
- "torch._utils._rebuild_tensor_v2"
What is a pickle import?
3.13 GB
LFS

update ckpt with 6ish epochs of training with 1024 TOKENS as max output over 2 years ago
rng_state_0.pth

14.5 kB
LFS

load model from drive and convert over 2 years ago
special_tokens_map.json

2.2 kB

load model from drive and convert over 2 years ago
tokenizer.json

2.42 MB

load model from drive and convert over 2 years ago
tokenizer_config.json

2.37 kB

update ckpt with 6ish epochs of training with 1024 TOKENS as max output over 2 years ago
trainer_state.json

7.06 kB

update ckpt with 6ish epochs of training with 1024 TOKENS as max output over 2 years ago
training_args.bin

4.53 kB
LFS

update ckpt with 6ish epochs of training with 1024 TOKENS as max output over 2 years ago
zero_to_fp32.py

18.9 kB

load model from drive and convert over 2 years ago

Detected Pickle imports (3)