Instructions to use dbaysal/code-unit-unlearning-meta_llama3_2_3b-prod_kl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use dbaysal/code-unit-unlearning-meta_llama3_2_3b-prod_kl with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-3B") model = PeftModel.from_pretrained(base_model, "dbaysal/code-unit-unlearning-meta_llama3_2_3b-prod_kl") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 09ad551248fcf937dcff4a21f287143813e403c1ce4e9a6eb5e8dd82718bb76d
- Size of remote file:
- 5.37 kB
- SHA256:
- 84a4af10967375c14e301d14de4cc2fb0dd08de787143b793044295016d7e030
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.