Instructions to use mehmetdavut/ruby3.4-llama-3.1-8b-1k-hq-4bit-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-1k-hq-4bit-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-1k-hq-4bit-gemini") - Notebooks
- Google Colab
- Kaggle
Download training_args.bin from mehmetdavut/ruby3.4-llama-3.1-8b-1k-hq-4bit-gemini: direct link, hf CLI and curl.
- Browser
- Download file 5.5 kB
-
https://huggingface.co/mehmetdavut/ruby3.4-llama-3.1-8b-1k-hq-4bit-gemini/resolve/main/training_args.bin
- Command line
-
hf download hf://mehmetdavut/ruby3.4-llama-3.1-8b-1k-hq-4bit-gemini/training_args.bin
-
curl -L -o training_args.bin https://huggingface.co/mehmetdavut/ruby3.4-llama-3.1-8b-1k-hq-4bit-gemini/resolve/main/training_args.bin
5.5 kB
- Xet hash:
- 6c2ef17ee167677699387cd4e6c5d057a7be2ab40fc8a4e5afa291204b4d0b95
- Size of remote file:
- 5.5 kB
- SHA256:
- ade1c6f8056b580cce155988b1815de3eaa22a22ef387906895d12dc076377eb
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.