Instructions to use LoftQ/Llama-2-13b-hf-bit4-rank64 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-rank64 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-rank64") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 78f4deeae2d03f1fde32be3926ff9a07400fc54ee889ca11dd5eb93ac286fcb1
- Size of remote file:
- 9.85 GB
- SHA256:
- 99dad634c71c32a855c77caf36dcfdde9bace20eeae42b661e51d594bbddd3f4
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.