Change some codes

Update

Fix an error

Fix an error

Merge branch 'main' of github.com:jesse-tong/docbert_knowledge_engineering_seminar

Fix an error

Update LICENSE.md

Update LICENSE.md

change license

hi

Change license and remove redundant data

modified: example_uses.md

Change arguments

print to console

Fix a bug in evaluation in multi-class

Reduce max sequence length to 250 as PhoBERT allows maximum 256 tokens

debug

delete debug

Delete debug vals

debug

debug

debug

debug

debug

debug

debug

debug

debug

Forget num_classes

Change loss function for multi-category because CrossEntropyLoss only accept outputs of (batch, x) and labels with shape of (batch)

Update requirements

First commit

Temporary fix

Temporary fix

Allow LSTM loading on CPU

Remove debugging code

Use BERT vocab size

test

test

Simplify distilling and inference

Simplify distilling

Fix LSTM tokenizer mismatch

Found a critical bug in LSTM inference when distillation using BERT Tokenizer but inference uses custom LSTM tokenizer

debug

Update inference_lstm

Update LSTM gradient clipping

Add layer normalization to LSTM model