Instructions to use mehmetdavut/ruby3.4-llama-3.2-3b-1k-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-3.2-3b-1k-hq-16bit-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-1k-hq-16bit-gemini") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from mehmetdavut/ruby3.4-llama-3.2-3b-1k-hq-16bit-gemini: direct link, hf CLI and curl.
- Browser
- Download file 17.2 MB
-
https://huggingface.co/mehmetdavut/ruby3.4-llama-3.2-3b-1k-hq-16bit-gemini/resolve/main/tokenizer.json
- Command line
-
hf download hf://mehmetdavut/ruby3.4-llama-3.2-3b-1k-hq-16bit-gemini/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/mehmetdavut/ruby3.4-llama-3.2-3b-1k-hq-16bit-gemini/resolve/main/tokenizer.json
17.2 MB
- Xet hash:
- dd3257fe3cb6a3b50407a5d58e1a89b83b019a11054f781437bb08900dbd38f3
- Size of remote file:
- 17.2 MB
- SHA256:
- f2f90a0ee1b41702c7b233b02234294a53bc0684a08d3bcd8c8ff702e9a12f64
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.