Instructions to use djroytburg/auditbench-llama33-70b-native-kto-hc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use djroytburg/auditbench-llama33-70b-native-kto-hc with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.3-70B-Instruct") model = PeftModel.from_pretrained(base_model, "djroytburg/auditbench-llama33-70b-native-kto-hc") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 23244d6040b48ded6ea958eb29e140ba884bc3cec2daadc484d7127d13b59097
- Size of remote file:
- 6.63 GB
- SHA256:
- 3239abd0730706040b0844d9e4ed8a9f7a83000909a250b7130ae11dca21d837
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.