Instructions to use seung/llama_custom_zero with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use seung/llama_custom_zero with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("NousResearch/Meta-Llama-3.1-8B-Instruct") model = PeftModel.from_pretrained(base_model, "seung/llama_custom_zero") - Notebooks
- Google Colab
- Kaggle
Download training_args.bin from seung/llama_custom_zero: direct link, hf CLI and curl.
- Browser
- Download file 5.43 kB
-
https://huggingface.co/seung/llama_custom_zero/resolve/main/training_args.bin
- Command line
-
hf download hf://seung/llama_custom_zero/training_args.bin
-
curl -L -o training_args.bin https://huggingface.co/seung/llama_custom_zero/resolve/main/training_args.bin
5.43 kB
- Xet hash:
- e4ee626c4f3e584c842d72e1603e79ffaf887e2c28b416cb542e4cb2d9c7d1b6
- Size of remote file:
- 5.43 kB
- SHA256:
- fb97a70cdace6dcf0026daeb68b873903d815c201455c5fde0998acb88cd09bf
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.