Instructions to use Chiaki111/phi4-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Chiaki111/phi4-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForSequenceClassification base_model = AutoModelForSequenceClassification.from_pretrained("microsoft/Phi-4-mini-instruct") model = PeftModel.from_pretrained(base_model, "Chiaki111/phi4-lora") - Transformers
How to use Chiaki111/phi4-lora with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Chiaki111/phi4-lora", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 9fabe0215d21e4d41111901e78f83b1aa5bd2b94c5ba9bca75f30aca5fc03578
- Size of remote file:
- 25.2 MB
- SHA256:
- b38e5374d04c8a42750eebdc061404656338af5ce33418e0850c75a16cc54f38
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.