Instructions to use mehmetdavut/ruby3.4-llama-3.1-8b-5k-hq-16bit-gemini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use mehmetdavut/ruby3.4-llama-3.1-8b-5k-hq-16bit-gemini with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.1-8B-Instruct") model = PeftModel.from_pretrained(base_model, "mehmetdavut/ruby3.4-llama-3.1-8b-5k-hq-16bit-gemini") - Notebooks
- Google Colab
- Kaggle
Download training_args.bin from mehmetdavut/ruby3.4-llama-3.1-8b-5k-hq-16bit-gemini: direct link, hf CLI and curl.
- Browser
- Download file 5.5 kB
-
https://huggingface.co/mehmetdavut/ruby3.4-llama-3.1-8b-5k-hq-16bit-gemini/resolve/main/training_args.bin
- Command line
-
hf download hf://mehmetdavut/ruby3.4-llama-3.1-8b-5k-hq-16bit-gemini/training_args.bin
-
curl -L -o training_args.bin https://huggingface.co/mehmetdavut/ruby3.4-llama-3.1-8b-5k-hq-16bit-gemini/resolve/main/training_args.bin
5.5 kB
- Xet hash:
- d0800df54fe7b169ae1ace5421a6dbb04b9df28da8f6b45c00e3c095566de535
- Size of remote file:
- 5.5 kB
- SHA256:
- 01ecee52af02772bb5beb882aaa28bfa13975b466fafcb671ae44beae6608ce9
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.