Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
amankhandelia
/
panini
like
0
Fill-Mask
Transformers
roberta
Inference Endpoints
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
7839b8e
panini
7 contributors
History:
63 commits
amank
Made change to cleaning code, modified number of warmpu step, getting eval samples from validation split
7839b8e
about 3 years ago
.vscode
Made change to cleaning code, modified number of warmpu step, getting eval samples from validation split
about 3 years ago
roberta_mc4_sentence_piece
Updated code to work with streaming version
about 3 years ago
.gitattributes
737 Bytes
Saving weights and logs of epoch 2
about 3 years ago
.gitignore
43 Bytes
Made change to cleaning code, modified number of warmpu step, getting eval samples from validation split
about 3 years ago
README.md
6.79 kB
Update README.md
about 3 years ago
config.json
692 Bytes
mc4 epoch14 exported torch config & tokenizer
about 3 years ago
create_config.py
147 Bytes
All set to train
about 3 years ago
flax_to_torch.py
793 Bytes
Convert latest model to PyTorch
about 3 years ago
merges.txt
1.21 MB
Pytorch export fix
about 3 years ago
run.sh
562 Bytes
Updated code to have different seed and reduced lr
about 3 years ago
run_mlm_flax.py
30.6 kB
Updated code to work with streaming version
about 3 years ago
run_mlm_flax_old.py
28.7 kB
Updated code to work with streaming version
about 3 years ago
run_mlm_flax_stream.py
27.5 kB
Made change to cleaning code, modified number of warmpu step, getting eval samples from validation split
about 3 years ago
run_stream.sh
673 Bytes
Made change to cleaning code, modified number of warmpu step, getting eval samples from validation split
about 3 years ago
special_tokens_map.json
239 Bytes
Pytorch export fix
about 3 years ago
tokenizer.json
2.86 MB
mc4 epoch14 exported torch config & tokenizer
about 3 years ago
tokenizer_config.json
279 Bytes
Pytorch export fix
about 3 years ago
train_tokenizer.py
1.08 kB
Updated code to work with streaming version
about 3 years ago
utils.py
1.96 kB
Made change to cleaning code, modified number of warmpu step, getting eval samples from validation split
about 3 years ago
vocab.json
1.55 MB
Pytorch export fix
about 3 years ago