Sheng Zha
Sheng Zha
On the [Question Answering with GluonNLP](https://nlp.gluon.ai/master/tutorials/question_answering/question_answering.html) - [ ] The mentions of `https://github.com/dmlc/gluon-nlp/tree/master/scripts/question_answering` should link to the example page so that we always refer to the source code in the...
On the [Tokenization - Part1: Basic Usage of Tokenizer and Vocabulary](https://nlp.gluon.ai/master/tutorials/tokenization/tokenization_part1.html) - [ ] `text processing workflow: raw text => normalized (cleaned) text => tokens => network` can be replaced...
For the tokenization notebooks, one pressing need I see is that there should be a reference page for the functionality of the CLIs in the API section. Otherwise, short of...
On [Compile NLP Models - Convert GluonNLP Models to TVM](https://nlp.gluon.ai/master/tutorials/deep_learning_compiler/tvm_basic.html) - [ ] At the moment this notebook includes only code and titles. We will need an introduction section for...
The ELECTRA-base 300k steps checkpoint can be found at https://szha-nlp.s3.amazonaws.com/output_electra_base/0300000.params. This should help reproduce the parameter loading issue in SQuAD fine-tuning.
@sxjscience I know that we hypothesized that the error in loading the pre-trained model in squad is due to parameter deduplication during saving, still it doesn't seem immediately obvious which...
#1527 adds a script to convert ElectraForPretrain parameters to ElectraModel version. SQuAD script doesn't allow specifying the generator dimension and layer scaling factors so the checkpoints are still not loadable...
@pjox thanks for letting us know, Pedro. Is there anything we can help with in terms of distribution? Let us know!
@utkarshsharma00 thanks for picking it up. Let us know if you need any help.