Kamal Raj Kanakarajan

Hi @NielsRogge, I have converted the SQA base TF1.X model to the TF2 model. You can check the code and model in this [repo](https://github.com/kamalkraj/TAPAS-TF2). You can use the notebook for...

Automatic download cache, resume download, Also automatically re-download if file in hub updated.

https://github.com/kamalkraj/CogView2/tree/gradio -Check readme Simple gradio interface. We can also run the backend alone using the replicate docker image ```bash docker run -d -p 5000:5000 --gpus=all r8.im/thudm/cogview2@sha256:8bd18a43f9113352683ea9fe70945e8150ad2b60bdb109ce74832e8b6c528d68 ``` And connect a...

@littlesulley What are the hyperparameters to reproduce results for ConLL2003 mentioned in the paper?

> BTW, the following are my outputs when I use ''batch_size=16, gradient_accumulation_steps=2'', I delete some of the middle outputs to make it shorter. In conll2003, usually (like LSTM+CRF) the F1...

@yhcc Thanks. Are you able to reproduce the results for the ConLL2003 dataset?

Hi @bes-dev, Thank you so much for sharing the onnx model. It will be really great if you can share the onnx conversion script for the `unet` model. Did you...

The Vakku2vec repo contains Language Model and News Classifier. Language Model representation cannot be visualized directly. But we have normal embeddings like GloVe on Malayalam which can be downloaded from...

ELECTRA TF - https://github.com/huggingface/transformers/pull/16104 ELECTRA PT - https://github.com/huggingface/transformers/pull/16103 DeBERTA PT - https://github.com/huggingface/transformers/pull/16105