| --- |
| base_model: WGLab/PoreFM-RNA |
| tags: |
| - porefm |
| - pytorch |
| - nanopore |
| - rna |
| - supervised-classifier |
| --- |
| |
| # PoreFM-RNA m6A / Inosine |
|
|
| Supervised PoreFM classifier for Oxford Nanopore RNA modification detection. |
|
|
| Model version: **0.1.0**. Chemistry: **RNA004**. Embedding dimension: **512**. |
|
|
| | File | Contents | |
| |---|---| |
| | `model.pt` | Complete backbone and classification head with preprocessing and modification-tag defaults. | |
|
|
| Class order: `A`, `m6A`, `Ino`. |
|
|
| Saved BAM-tag defaults: base `A`; modification codes `a`, `17596`, corresponding to `m6A`, `Ino`. |
|
|
| Model configuration and preprocessing are embedded in the checkpoints. Setup and usage are documented in the PoreFM code repository. |
|
|
| `manifest.json` records artifact identities and tensor fingerprints. `SHA256SUMS` verifies checkpoint downloads. Tensor fingerprints are independent of descriptive metadata; file hashes identify exact bytes. Documentation-only changes leave the model version unchanged. |
|
|
