PEFT
Safetensors
mistral
alignment-handbook
Generated from Trainer
trl
sft
4-bit precision
bitsandbytes
Instructions to use erbacher/zephyr-7b-proimg-qlora-user with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use erbacher/zephyr-7b-proimg-qlora-user with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("HuggingFaceH4/zephyr-7b-beta") model = PeftModel.from_pretrained(base_model, "erbacher/zephyr-7b-proimg-qlora-user") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 6e8f6e941b07a350c86049aa79b0bb40ea44d3b8fb909006d9c80f243c90f9e0
- Size of remote file:
- 83.9 MB
- SHA256:
- 5e7e38cc2d62c7a252c54b7bd08f7fcf0880adf53bee26e7b2a91e166c214f87
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.