Instructions to use LoftQ/Llama-2-13b-hf-bit4-rank32 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use LoftQ/Llama-2-13b-hf-bit4-rank32 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-13b-hf") model = PeftModel.from_pretrained(base_model, "LoftQ/Llama-2-13b-hf-bit4-rank32") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 69e10be4fc810f67ca3aa617a9747827de9c734e40d1aa3640f9b8e85e19aeb2
- Size of remote file:
- 2.79 GB
- SHA256:
- 3d0b61a9d68fc00969e11afa247f3904224a1643317a6bb177fb5db08f4c0063
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.