Instructions to use WillHeld/DiVA-llama-3-v0-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use WillHeld/DiVA-llama-3-v0-8b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="WillHeld/DiVA-llama-3-v0-8b", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("WillHeld/DiVA-llama-3-v0-8b", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Training Code
#2
by setianke - opened
Hello, awesome model! Thank you for sharing. Is there any training code available to continue the training of the model? Thank you
Hi @setianke !
Glad the model is of interest!
Currently, all the relevant code is linked at the top of the page here: https://diva-audio.github.io/
This includes the Levanter training code that was used to produce DiVA and can be reused for other applications!
WillHeld changed discussion status to closed