keras-nlp
keras-nlp copied to clipboard
Modular Natural Language Processing workflows with Keras
**Describe the bug** UserWarnings are presented when a mask is propagated via mask_zero=True to TransformerDecoder. Considering this is the default behavior, a warning is confusing and a nuisance. **To Reproduce**...
Assigned to integrate "D-FINE: Redefine Regression Task of DETRs as Fine‑grained Distribution Refinement" into KerasHub. **Links:** **GitHub:** https://github.com/Peterande/D-FINE **Paper Link:** https://arxiv.org/abs/2410.13842 **Transformers:** https://huggingface.co/docs/transformers/main/en/model_doc/d_fine
## Description This PR fixes the LayoutLMv3 checkpoint conversion script to properly handle different spatial embedding dimensions between the base and large models. The base model uses 128 dimensions for...
Good day, I wanted to know if I could take up Cohere and Cohere2 as my next two models to integrate into KH. The Command series' performance is recognized in...
Since KerasHub has evolved, updating the model contribution guides. This will make contributions consistent and lower review time. Markdown preview here https://github.com/divyashreepathihalli/keras-nlp/blob/contributing_guide/CONTRIBUTING_MODELS.md
Qwen2 VL and Qwen 2.5 VL are excellent model consistently topping lmsys leaderboards. We must have them in the library. I'll work on it.
Ref: #2027
InceptionNet
Adding InceptionNet backbone Functionalities...