You can deploy this model and start earning money today!

soda-research/
discrete-audio-isoflop-1.8e19-851M-d1408-L14-B16-f133cc

Name: discrete-audio-isoflop-1.8e19-851M-d1408-L14-B16-f133cc
Availability: InStock

next-token-prediction

isoflop

research

apache-2.0

Views

No views yet

Discrete Audio IsoFLOP Model (discrete-audio-isoflop-1.8e19-851M-d1408-L14-B16-f133cc)

A suite of discrete audio models trained for our IsoFLOP study as part of SODA, which is a unified next-token prediction on interleaved semantic, acoustic, and text tokens.

🥤 Project Page: https://soda-audio.github.io

For full usage instructions (e.g., inference code), and more information, please refer to the SODA-4B-base model card.

The details for this particular model is as follows:

compute_budget: 1.8e19
param_count (non-embedding): 851M
hidden_dim: 1408
num_layers: 14
batch_size: 16
training_step: 56502
hash_key: f133cc

📈 WandB: https://wandb.ai/potsawee/marin/groups/IsoFlop/workspace

soda-research/discrete-audio-isoflop-1.8e19-851M-d1408-L14-B16-f133cc

Discrete Audio IsoFLOP Model (discrete-audio-isoflop-1.8e19-851M-d1408-L14-B16-f133cc)

soda-research/
discrete-audio-isoflop-1.8e19-851M-d1408-L14-B16-f133cc