Instructions to use Nandini82/ft-adapters with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Nandini82/ft-adapters with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("NousResearch/Llama-2-7b-chat-hf") model = PeftModel.from_pretrained(base_model, "Nandini82/ft-adapters") - Notebooks
- Google Colab
- Kaggle
Download adapter_model.bin from Nandini82/ft-adapters: direct link, hf CLI and curl.
- Browser
- Download file 134 MB
-
https://huggingface.co/Nandini82/ft-adapters/resolve/main/adapter_model.bin
- Command line
-
hf download hf://Nandini82/ft-adapters/adapter_model.bin
-
curl -L -o adapter_model.bin https://huggingface.co/Nandini82/ft-adapters/resolve/main/adapter_model.bin
134 MB
- Xet hash:
- aebe886e8170811605602726b71a9f23f033d4a67ebda3eb8ff62527086d214d
- Size of remote file:
- 134 MB
- SHA256:
- b1dca3a0599285bc202e786f83a816cea34e8d69abecbedc396e6a2f1e96681b
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.