PEFT
Safetensors
llama
audio
video
segmentation
mask-quality-assessment
audio-visual-segmentation
lora
Instructions to use Jinxing1/MQ-Auditor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Jinxing1/MQ-Auditor with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/home/panwen.hu/workspace1/jinxing.zhou/mllm/Crab/pretrained_weights/Llama-2-7b-chat-hf") model = PeftModel.from_pretrained(base_model, "Jinxing1/MQ-Auditor") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 80752099030786a0cd635bd256a6cbdc03cd9c2eebc9fe9b87b026f9c7073ed7
- Size of remote file:
- 817 MB
- SHA256:
- 54f177714a6a06e6d5564e47a87dacb11359eef4fae90efe93a4d3efa044ae61
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.