flax-community
/

roberta-pretraining-hindi

Model card Files Files and versions

Metrics Training metrics Community

roberta-pretraining-hindi

1.04 GB

Ctrl+K

Ctrl+K

5 contributors

History: 38 commits

dk-crazydiv's picture

mc4 epoch14

9142843 over 4 years ago

.gitattributes

737 Bytes
Saving weights and logs of epoch 2 almost 5 years ago
README.md

162 Bytes
Updated README almost 5 years ago
config.json

670 Bytes
Updated torch model and fixed typo in conversion script almost 5 years ago
create_config.py

147 Bytes
All set to train almost 5 years ago
events.out.tfevents.1625416432.t1v-n-9df4ce0e-w-0.447041.3.v2

40 Bytes
xet

Saving weights and logs of epoch 1 almost 5 years ago
events.out.tfevents.1625418057.t1v-n-9df4ce0e-w-0.452509.3.v2

41.6 MB
xet

Saving weights and logs of epoch 8 almost 5 years ago
flax_model.msgpack

499 MB
xet

mc4 epoch14 over 4 years ago
flax_to_torch.py

805 Bytes
Updated torch model and fixed typo in conversion script almost 5 years ago
pytorch_model.bin
Detected Pickle imports (4)
- "torch.FloatStorage",
- "torch.LongStorage",
- "torch._utils._rebuild_tensor_v2",
- "collections.OrderedDict"
What is a pickle import?
499 MB
xet

Converted latest model to torch model almost 5 years ago
run.sh

562 Bytes
Updated code to have different seed and reduced lr almost 5 years ago
run_mlm_flax.py

28.7 kB
Fix on lr almost 5 years ago
tokenizer.json

2.86 MB
mc4 epoch2 almost 5 years ago
train_tokenizer.py

776 Bytes
tzz almost 5 years ago