Instructions to use pe4enov/saiga_7b_lora_8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use pe4enov/saiga_7b_lora_8bit with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("huggyllama/llama-7b") model = PeftModel.from_pretrained(base_model, "pe4enov/saiga_7b_lora_8bit") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 437a19f7784791aeb721b5a8e3f22136b7acbcc291926880c0adfad180b5b1ad
- Size of remote file:
- 160 MB
- SHA256:
- de77b76deac9594910c8eab25fe7ddc56c2605daae60396a607f37f87bad12ca
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.