Ctrl+K

8 contributors

History: 22 commits

versae

Adding base config and organizing configs

9c5541b about 4 years ago

configs
Adding base config and organizing configs about 4 years ago
mc4
Adding sampling to mc4 about 4 years ago
.gitattributes

690 Bytes

initial commit about 4 years ago
.gitignore

1.84 kB

Initial test with BETO's corpus about 4 years ago
README.md

1.84 kB

Adding checkpointing, wandb, and new mlm script about 4 years ago
config.py

247 Bytes

Scripts for perplexity sampling and fixes about 4 years ago
convert.py

458 Bytes

Scripts for perplexity sampling and fixes about 4 years ago
flax_model.msgpack

712 MB
xet

Adding correct models 10k steps about 4 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. about 4 years ago
perplexity.py

751 Bytes

Adding checkpointing, wandb, and new mlm script about 4 years ago
pytorch_model.bin

1.42 GB
xet

Adding correct models 10k steps about 4 years ago
run.sh

883 Bytes

Adding base config and organizing configs about 4 years ago
run_mlm_flax.py

30 kB

Adding sampling to mc4 about 4 years ago
run_mlm_flax_stream.py

28 kB

Adding sampling to mc4 about 4 years ago
run_stream.sh

924 Bytes

Adding base config and organizing configs about 4 years ago
tokenizer.json

1.47 MB

New tokenizer about 4 years ago
tokens.py

649 Bytes

Scripts for perplexity sampling and fixes about 4 years ago
tokens.py.orig

899 Bytes

Adjust batch size for extrating tokens about 4 years ago
tsne_plot.py

3.02 kB

Remove unused imports about 4 years ago