PSL_E0_corrected_v5 is an open-weight model from Muhammad Usman. Its published files total 3.3 GB.
Parameters—
Context—
Weights3.3 GB
License—
AccessOpen weights
Monthly Downloads—
Model Card
The publisher has not written a card for this model.
Identity and Version
- Repository
- em-usman25/PSL_E0_corrected_v5
- Publisher
- Muhammad Usman
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- c6268157beb131139da61b0da7037237ee356b3f
- First published
- 2026-09-18
- Last updated
- 2026-09-19
Files and Weights
14 files, 3.3 GB in total. The weights are 5 files totalling 3.3 GB in npz, pth.
Weights5 files · 3.3 GB
Configuration1 file · 4.4 KB
Other7 files · 523.5 KB
Repository1 file · 1.7 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| best_seed1337.pth | Weights | 414.8 MB | 375c85545e0c |
| best_seed42.pth | Weights | 414.8 MB | 1857501bf2f3 |
| ckpt_seed1337.pth | Weights | 1.2 GB | d3c1b32728ff |
| ckpt_seed42.pth | Weights | 1.2 GB | 597d807c5ee3 |
| test_preds_seed42.npz | Weights | 415.4 KB | 1ef51eacd2ca |
| results_seed42.json | Configuration | 4.4 KB | — |
| best_worst_classes_seed42.png | Other | 113.6 KB | 89be99bd1bb9 |
| classification_report_seed42.csv | Other | 5.8 KB | — |
| confusion_matrix_seed42.png | Other | 105.1 KB | e4aac4674b44 |
| per_class_accuracy_seed42.png | Other | 72.2 KB | — |
| per_class_seed42.csv | Other | 2.5 KB | — |
| top20_confused_seed42.png | Other | 96.4 KB | — |
| training_curves_seed42.png | Other | 127.9 KB | 3c7ceae9b309 |
| .gitattributes | Repository | 1.7 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 3.3 GB
Download from Muhammad Usman
Released by Muhammad Usman through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 3.3 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.