Instructions to use deniselj24/llama-2-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use deniselj24/llama-2-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("togethercomputer/llama-2-7b") model = PeftModel.from_pretrained(base_model, "deniselj24/llama-2-lora") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 7f6fec1c8a2c964da72abe884174eff6ba3d2be023a134eed2a2ff538ebc31f4
- Size of remote file:
- 33.6 MB
- SHA256:
- a369ea6ce64d558a21da3abb3375d82484ff77bc2648898e2f9e21bf14dee089
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.