Instructions to use jianqiang0213/mdeberta-v3-MX-binary-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use jianqiang0213/mdeberta-v3-MX-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-MX-binary-lora") - Transformers
How to use jianqiang0213/mdeberta-v3-MX-binary-lora with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("jianqiang0213/mdeberta-v3-MX-binary-lora", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- c44ae352bfb6735862e2c4cd6e6e0ccd5de6a5248f739dc0f18baad7108597d8
- Size of remote file:
- 5.91 kB
- SHA256:
- 25784bd60b1674a7ebe34ccd38e5116d69adba66237d01205e64dd5fba8da107
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.