Instructions to use mehmetdavut/ruby3.4-llama-3.2-3b-5k-all-8bit-gemini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use mehmetdavut/ruby3.4-llama-3.2-3b-5k-all-8bit-gemini with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-3B-Instruct") model = PeftModel.from_pretrained(base_model, "mehmetdavut/ruby3.4-llama-3.2-3b-5k-all-8bit-gemini") - Notebooks
- Google Colab
- Kaggle
Download adapter_model.safetensors from mehmetdavut/ruby3.4-llama-3.2-3b-5k-all-8bit-gemini: direct link, hf CLI and curl.
- Browser
- Download file 97.3 MB
-
https://huggingface.co/mehmetdavut/ruby3.4-llama-3.2-3b-5k-all-8bit-gemini/resolve/main/adapter_model.safetensors
- Command line
-
hf download hf://mehmetdavut/ruby3.4-llama-3.2-3b-5k-all-8bit-gemini/adapter_model.safetensors
-
curl -L -o adapter_model.safetensors https://huggingface.co/mehmetdavut/ruby3.4-llama-3.2-3b-5k-all-8bit-gemini/resolve/main/adapter_model.safetensors
97.3 MB
- Xet hash:
- fe2c4d464b208bc2212384d97aa3b135ed63ad8631fa8f7b65c87bc1bd40927d
- Size of remote file:
- 97.3 MB
- SHA256:
- 27c791528eeb76be09862d45db960736040e7a7c6754e2a85562cb24ec6aa6c8
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.