Llama-2-13b-hf - bnb 4bit
- Model creator: Meta
- Original model: Llama-2-13b-hf
Description
This model is 4bit quantized version of Llama-2-13b-hf using bitsandbytes. It's designed for fine-tuning! The PAD token is set as UNK.
leliuga/Llama-2-13b-hf-bnb-4bit
Submit in one command
Run it next to your model folder. It makes the torrent, checks your files against Hugging Face, and submits it. You just start seeding and paste your key from your account. It only reads your files and never changes them. Read the script first if you like.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo leliuga/Llama-2-13b-hf-bnb-4bit ./model-folder