Release 0.1.0

README.md

@@ -0,0 +1,27 @@
+---
+base_model: WGLab/PoreFM-DNA
+tags:
+  - porefm
+  - pytorch
+  - nanopore
+  - dna
+  - supervised-classifier
+---
+
+# PoreFM-DNA BrdU / EdU
+
+Supervised PoreFM classifier for Oxford Nanopore DNA modification detection.
+
+Model version: **0.1.0**. Chemistry: **R10.4.1 (E8.2, 400 bps)**. Embedding dimension: **384**.
+
+| File | Contents |
+|---|---|
+| `model.pt` | Complete backbone and classification head with preprocessing and modification-tag defaults. |
+
+Class order: `T`, `BrdU`, `EdU`.
+
+Saved BAM-tag defaults: base `T`; modification codes `472552`, `232486`, corresponding to `BrdU`, `EdU`.
+
+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.

SHA256SUMS

@@ -0,0 +1 @@
+0b5a351fc4fcfd03333ba3ddfc412af8e7d91dc53b51b0ead7b673cbf4ee54a3  model.pt

manifest.json

@@ -0,0 +1,42 @@
+{
+  "schema_version": 1,
+  "model_name": "PoreFM-DNA BrdU / EdU",
+  "model_version": "0.1.0",
+  "embedding_dim": 384,
+  "chemistry": "dna_r10.4.1_e8.2_400bps",
+  "molecule_type": "dna",
+  "class_labels": [
+    "T",
+    "BrdU",
+    "EdU"
+  ],
+  "base": "T",
+  "mod_code": [
+    "472552",
+    "232486"
+  ],
+  "artifacts": [
+    {
+      "file": "model.pt",
+      "size_bytes": 81331759,
+      "file_sha256": "0b5a351fc4fcfd03333ba3ddfc412af8e7d91dc53b51b0ead7b673cbf4ee54a3",
+      "role": "supervised_classifier",
+      "format": "pytorch_checkpoint",
+      "tensor_fingerprint": {
+        "scheme": "porefm-tensor-content-v1",
+        "sha256": "d57dd81e306efb1b007abb4a570ba405769c6d95dc0680110aabfdc1b3672bd8"
+      }
+    }
+  ],
+  "tensor_fingerprint_scheme": {
+    "name": "porefm-tensor-content-v1",
+    "algorithm": "sha256",
+    "scope": "Stored tensors and numeric arrays, including their names, shapes and dtypes; scalar configuration and other metadata are excluded.",
+    "encoding": [
+      "Initialize SHA-256 with ASCII porefm-tensor-content-v1 followed by one zero byte.",
+      "Recursively traverse dictionaries sorted by (type(key).__name__, str(key)), and lists/tuples in index order. Skip leaves other than torch.Tensor and numpy.ndarray.",
+      "For each leaf, compact ASCII-escaped UTF-8 JSON encodes [key_path, dtype, shape, nbytes]. key_path is the list of dictionary keys and sequence indices. dtype is torch: plus str(tensor.dtype), or numpy: plus array.dtype.str.",
+      "Append the JSON byte length as an unsigned 8-byte big-endian integer, the JSON bytes, then C-contiguous numerical bytes in little-endian representation. Tensor/array storage padding is excluded."
+    ]
+  }
+}

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b5a351fc4fcfd03333ba3ddfc412af8e7d91dc53b51b0ead7b673cbf4ee54a3
+size 81331759