1from huggingface_hub import hf_hub_download
2
3ckpt_path = hf_hub_download(
4 repo_id="junchenfu/diger-rqvae-instruments",
5 filename="best_collision_model.pth",
6)
The checkpoint can be loaded with the RQ-VAE implementation in the DIGER GitHub repository:
Please refer to the repository README for the full training configuration and commands.
LLaMA embeddings used by DIGER should be generated following the procedure described in:
The underlying recommendation datasets are publicly available from their original sources. Processed interaction data are not hosted in this model repository; they can be regenerated following the DIGER codebase.
If you use this checkpoint, please cite the DIGER paper.