Hey,
My goal is to use the mamba model for the task of token classification and I’m a bit lost at this point. I use a dataset which is similar to the conll2003 dataset.
The tries I have done till now where all based on these resources:
- Emotion Tuned Sarcasm - Notebook by Raj Sangani (rajbsangani) | Jovian
- Implemented MambaForSequenceClassification by Adibvafa · Pull Request #31155 · huggingface/transformers · GitHub
i will add a bit of code later…
It would be nice to get some guidance to start fresh.