6 contributors

History: 44 commits

versae

Adding pad_to_multiple_of=16

986ff4e almost 3 years ago

configs
Changed and added vocab and tokenizer almost 3 years ago
mc4
Fixes to mc4 fork almost 3 years ago
.gitattributes

736 Bytes

Update .gitattributes almost 3 years ago
.gitignore

1.84 kB

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

1.84 kB

Fixed widget example almost 3 years ago
config.json

618 Bytes

Fix config for checkpoint almost 3 years ago
config.py

256 Bytes

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

876 Bytes

Improved version of conversion script Flax → PyTorch almost 3 years ago
flax_model.msgpack

499 MB
LFS

Fix config for checkpoint almost 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. almost 3 years ago
merges.txt

505 kB

Changed and added vocab and tokenizer almost 3 years ago
perplexity.py

751 Bytes

Adding checkpointing, wandb, and new mlm script almost 3 years ago
pytorch_model.bin

499 MB
LFS

Fix config for checkpoint almost 3 years ago
run.sh

883 Bytes

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

30 kB

Adding sampling to mc4 almost 3 years ago
run_mlm_flax_stream.py

30.8 kB

Adding pad_to_multiple_of=16 almost 3 years ago
run_stream.sh

932 Bytes

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

239 Bytes

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

1.45 MB

Changed and added vocab and tokenizer almost 3 years ago
tokenizer_config.json

292 Bytes

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

649 Bytes

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

899 Bytes

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

3.02 kB

Remove unused imports almost 3 years ago
vocab.json

846 kB

Changed and added vocab and tokenizer almost 3 years ago