Instructions to use anjohn0077/NEXS-toxicity-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use anjohn0077/NEXS-toxicity-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.1-8B") model = PeftModel.from_pretrained(base_model, "anjohn0077/NEXS-toxicity-lora") - Notebooks
- Google Colab
- Kaggle
Replace raw extraction with sanitized vLLM-ready toxicity LoRA (pure lora_A/lora_B, modules_to_save stripped; source: K-intelligence/Llama-SafetyGuard-Content-Binary)
e274afb verified - Xet hash:
- 22d8b6fdb9eeef1975bb94930d9a7f435ead4c55cd8c76d917d32ed1d7c5787f
- Size of remote file:
- 671 MB
- SHA256:
- 06cae39836b2cb969b0cd9f107d8b57c5b942af222078f611e381d9ec5fc8cfa
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.