Instructions to use odunola/hack_data with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use odunola/hack_data with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("bigscience/bloomz-3b") model = PeftModel.from_pretrained(base_model, "odunola/hack_data") - Notebooks
- Google Colab
- Kaggle
Download adapter_model.bin from odunola/hack_data: direct link, hf CLI and curl.
- Browser
- Download file 19.7 MB
-
https://huggingface.co/odunola/hack_data/resolve/main/adapter_model.bin
- Command line
-
hf download hf://odunola/hack_data/adapter_model.bin
-
curl -L -o adapter_model.bin https://huggingface.co/odunola/hack_data/resolve/main/adapter_model.bin
19.7 MB
- Xet hash:
- eb8bd4c8cab02eb8b93c870f27a5a0cf4d40c32faebacfe5f291eca06710fb04
- Size of remote file:
- 19.7 MB
- SHA256:
- e3863dd55669dbb4acb7e93539d161a489f8b6041d7bcfd8cdc4367c1bbd7ec4
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.