Instructions to use jianqiang0213/mdeberta-v3-TR-binary-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use jianqiang0213/mdeberta-v3-TR-binary-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForSequenceClassification base_model = AutoModelForSequenceClassification.from_pretrained("microsoft/mdeberta-v3-base") model = PeftModel.from_pretrained(base_model, "jianqiang0213/mdeberta-v3-TR-binary-lora") - Transformers
How to use jianqiang0213/mdeberta-v3-TR-binary-lora with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("jianqiang0213/mdeberta-v3-TR-binary-lora", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 21e51e4cf0aa156e193a957b19ed3d97612d3cfb984658f7ab680ac51f79e47a
- Size of remote file:
- 5.91 kB
- SHA256:
- 2655c29fddf1284a95d002d1d753d14149873f8a871f8323118c83394c498feb
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.