Instructions to use paul21/llama-30b-20 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use paul21/llama-30b-20 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/gpfsscratch/rech/cwa/umm59ig/llm/llama-30b") model = PeftModel.from_pretrained(base_model, "paul21/llama-30b-20") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 978945de21c34222355cff7103569a485ecdf61704ca850cbc4516d4a1a2d0fa
- Size of remote file:
- 153 MB
- SHA256:
- 22199dd47ac605f522c51ed18dac1094c91bad9587fa88e8dba7ee6fec6596fb
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.