Downloads · 30 days
14
3% of all-time downloads
soda-600m-prelim
soda-research/soda-600m-prelim
soda-600m-prelim is a machine learning model from soda-research. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
SODA (Scaling Open Discrete Audio) is a suite of discrete audio foundation models using next-token prediction on interleaved semantic, acoustic, and text tokens.
All-time downloads
495
Public
Parameters
649M
2.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.6 GB · 99%
At a glance
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Feb 4, 2026
- Updated
- Feb 13, 2026
- SHA
- 144b0b15
Model card
From the Hugging Face model README
🥤 SODA Preliminary Run
SODA (Scaling Open Discrete Audio) is a suite of discrete audio foundation models using next-token prediction on interleaved semantic, acoustic, and text tokens.
🌐 Project Page: https://soda-audio.github.io
This model is part of our SODA Research collection (e.g., IsoFLOP sweep, preliminary runs, or ablations).
Note that this model (soda-600m-prelim) is the same model as in https://huggingface.co/WillHeld/blueberry
As an preliminary experiment, we were not strict with our data criterion, and we ended up training this model on multiple languages (%ratio) as follows: including English (72.52%), Spanish (15.04%), French (7.13%), German (4.73%), Thai (0.20%), Hindi (0.16%), Arabic (0.12%), Chinese (0.10%). This model was trained on 500B tokens in total.
For full usage instructions, and more information, please refer to the SODA-4B-base model card:
👉 SODA-4B-base
📈 WandB: https://wandb.ai/marin-community/marin/runs/exp1699_marin_yodas2-b5edae/
- Type
- qwen3
- License
- apache-2.0
- Languages
- en, es, fr, de, th, hi
- Created
- Feb 4, 2026
- Updated
- Feb 13, 2026