8 contributors

History: 194 commits

elishowk

Automatic correction of README.md metadata. Contact [email protected] for any question

389b7ab about 3 years ago

configs
Changed and added vocab and tokenizer over 3 years ago
evaluation
Adding stepwise 512 and fixing some markdown warnings over 3 years ago
images
image style update over 3 years ago
mc4
Add eval scripts over 3 years ago
utils
Fixes and eval configs over 3 years ago
.gitattributes

737 Bytes

initial commit over 3 years ago
.gitignore

1.84 kB

Initial test with BETO's corpus over 3 years ago
README.md

42.8 kB

Automatic correction of README.md metadata. Contact [email protected] for any question about 3 years ago
config.json

618 Bytes

Fix config for checkpoint over 3 years ago
config.py

256 Bytes

Preparing code for final runs over 3 years ago
convert.py

876 Bytes

Improved version of conversion script Flax → PyTorch over 3 years ago
events.out.tfevents.1625704081.t1v-n-a4d97d44-w-0.212075.3.v2

40 Bytes
LFS

Adding tfevents over 3 years ago
events.out.tfevents.1625704245.t1v-n-a4d97d44-w-0.216676.3.v2

40 Bytes
LFS

Adding tfevents over 3 years ago
events.out.tfevents.1625705283.t1v-n-a4d97d44-w-0.234462.3.v2

40 Bytes
LFS

Adding tfevents over 3 years ago
flax_model.msgpack

250 MB
LFS

Gaussian 128 over 3 years ago
get_embeddings_and_perplexity.py

1.53 kB

Add script to generate dataset of embeddings and perplexities. Add script to generate t-SNE plot for embedding and perplexity visualization. over 3 years ago
merges.txt

514 kB

Version 1.0 :fire: over 3 years ago
perplexity.py

751 Bytes

Adding checkpointing, wandb, and new mlm script over 3 years ago
pytorch_model.bin
Detected Pickle imports (4)
- "torch.FloatStorage",
- "torch.LongStorage",
- "collections.OrderedDict",
- "torch._utils._rebuild_tensor_v2"
What is a pickle import?
499 MB
LFS

Gaussian 128 over 3 years ago
run.sh

883 Bytes

Adding base config and organizing configs over 3 years ago
run_mlm_flax.py

30 kB

Adding sampling to mc4 over 3 years ago
run_mlm_flax_stream.py

35.2 kB

Fixes and eval configs over 3 years ago
run_stream.sh

932 Bytes

Preparing code for final runs over 3 years ago
special_tokens_map.json

239 Bytes

Changed and added vocab and tokenizer over 3 years ago
tokenizer.json

1.47 MB

Version 1.0 :fire: over 3 years ago
tokenizer_config.json

292 Bytes

Changed and added vocab and tokenizer over 3 years ago
tokens.py

649 Bytes

Scripts for perplexity sampling and fixes over 3 years ago
tokens.py.orig

899 Bytes

Adjust batch size for extrating tokens over 3 years ago
tsne_plot.py

3.02 kB

Remove unused imports over 3 years ago
vocab.json

855 kB

Version 1.0 :fire: over 3 years ago

Detected Pickle imports (4)