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 adapter_model.safetensors from mehmetdavut/ruby3.4-llama-3.1-8b-5k-hq-16bit-gemini: direct link, hf CLI and curl.
- Browser
- Download file 168 MB
-
https://huggingface.co/mehmetdavut/ruby3.4-llama-3.1-8b-5k-hq-16bit-gemini/resolve/main/adapter_model.safetensors
- Command line
-
hf download hf://mehmetdavut/ruby3.4-llama-3.1-8b-5k-hq-16bit-gemini/adapter_model.safetensors
-
curl -L -o adapter_model.safetensors https://huggingface.co/mehmetdavut/ruby3.4-llama-3.1-8b-5k-hq-16bit-gemini/resolve/main/adapter_model.safetensors
168 MB
- Xet hash:
- 9ad0b3a1924e4a665fb840c9559f433d711340cc65a54c1348ef44dc822150f4
- Size of remote file:
- 168 MB
- SHA256:
- fb93f6b263c1e5768e1bb4722d397611c2a1550163f7493aed54696d76a3e35b
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.