Instructions to use lora-moe/belle_dolphine_p17 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use lora-moe/belle_dolphine_p17 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("baichuan-inc/Baichuan2-7B-Base") model = PeftModel.from_pretrained(base_model, "lora-moe/belle_dolphine_p17") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 4d0a52e22fa54f1130bf11aa385646e91939425105241cd71bad8997f16c09e4
- Size of remote file:
- 2 MB
- SHA256:
- 79452955be6b419a65984273a9f08af86042e1c2a75ee3ba989cbf620a133cc2
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.