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:
- fd59215876a8f42a138c48c51e491c4d196d247e47335f7d396fdeb5331e3151
- Size of remote file:
- 307 MB
- SHA256:
- 701bdff246f33e1887e3a0b134678f698f4e25558ba95312fc2172aea1b5a0ae
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.