Instructions to use nvidia/personaplex-7b-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Moshi
How to use nvidia/personaplex-7b-v1 with Moshi:
# pip install moshi # Run the interactive web server python -m moshi.server --hf-repo "nvidia/personaplex-7b-v1" # Then open https://localhost:8998 in your browser
# pip install moshi import torch from moshi.models import loaders # Load checkpoint info from HuggingFace checkpoint = loaders.CheckpointInfo.from_hf_repo("nvidia/personaplex-7b-v1") # Load the Mimi audio codec mimi = checkpoint.get_mimi(device="cuda") mimi.set_num_codebooks(8) # Encode audio (24kHz, mono) wav = torch.randn(1, 1, 24000 * 10) # [batch, channels, samples] with torch.no_grad(): codes = mimi.encode(wav.cuda()) decoded = mimi.decode(codes) - Notebooks
- Google Colab
- Kaggle
Create Initiative and Request
#18
by Niroop-2007 - opened
Thank You NVIDIA For contributing a lot for us developers - I was unable to contact you Directly - so i expect Hugging Face Portal to be a good means of communication - World is running over AI with Policies - why not simulate a Restricted virtual environment [ Means to simulate everything whats there in a Public sector & execute AGI Systems - if you can give me an opportunity to contact you - i would like to propose the beginning few projects i have been making with PersonaPlex 7B V1 ] - It is helpful for the public domain - only with your permission i would like to do something for the people - As Jensen sir ! You have been my Inspiration
I am very sorry to tell you that a company that wants to maximize their profit is not going to care about your projects/ideas. The only thing that tech giants want is more and more money.
It is better to go ahead and implement your ideas than making proposals. You don't need our permission. PersonaPlex is an open model, so feel free to build any project that you desire!
royrajarshi changed pull request status to closed