Instructions to use tsinghua-ee/video-SALMONN-2_plus_7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use tsinghua-ee/video-SALMONN-2_plus_7B with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("output/audio_align_winqf0_5s_Ls960Com_AcSl_bs8ep5_LargerQF/checkpoint-30510") model = PeftModel.from_pretrained(base_model, "tsinghua-ee/video-SALMONN-2_plus_7B") - Notebooks
- Google Colab
- Kaggle
Need help leveraging this model
#2
by samikshro - opened
I am attempting to use this model on a Google Colab, but there appears to be a lack of documentation on how to get started, or likely I am misunderstanding.
Is there a possibility for the researchers to post a Colab of the model being used? Such that we may replicate your processes for testing?