Downloads · 30 days
20
100% of all-time downloads
anikakumar/perceiver-multitask-2024
perceiver-multitask-2024 is a machine learning model from anikakumar. 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 bsd-3-clause.
A research-oriented Perceiver prototype targeting Multitask. The included giant setup documents defaults and file formats without presenting unverified performance numbers.
Downloads · 30 days
20
100% of all-time downloads
All-time downloads
20
Public
Parameters
49.6K
199 KB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors199 KB · 97%
From the Hugging Face model README
A research-oriented Perceiver prototype targeting Multitask. The included giant setup documents defaults and file formats without presenting unverified performance numbers.
config.json records the generated architecture settings.training_args.json records the default experiment recipe.model.safetensors is a valid initialization checkpoint for smoke tests; it is not presented as a trained benchmark checkpoint.| Item | Value |
|---|---|
| Architecture | Perceiver |
| Scale | giant |
| Attention | sparse |
| Fusion | cross attention |
| Activation | approx gelu |
| Normalization | rmsnorm |
The included configuration uses adamw with a constant warmup schedule. These are starting values in the script, not evidence of a completed run. For a meaningful evaluation, train all baselines with the same data exposure, tuning budget, and random seeds.
python eval.py --help
Inspect the script's __main__ block for its generated smoke-test example. Because this is a custom implementation, generic automatic loading APIs require an explicit adapter before use.
A useful first evaluation would use a task-specific held-out set, report the task metric across at least three seeds, and include a matched-capacity baseline. Keep training logs and environment versions with any published result.
The initialization checkpoint has not been trained or audited for robustness, fairness, or domain transfer. The implementation should be treated as an experimental starting point. Results from a future trained checkpoint must be documented separately from the defaults shipped here.
eval.py — primary artifactREADME.md — this documentationconfig.json — architecture configurationtraining_args.json — default experiment settingsmodel.safetensors — initialization checkpointReleased under bsd-3-clause. Review the source-data terms separately when this repository is used with external datasets.