Release 0.1.0

README.md

@@ -1,3 +1,23 @@
 ---
-license: mit
+tags:
+  - porefm
+  - pytorch
+  - nanopore
+  - rna
+  - pretrained
 ---
+
+# PoreFM-RNA
+
+Pretrained PoreFM model for Oxford Nanopore RNA signals.
+
+Model version: **0.1.0**. Chemistry: **RNA004**. Embedding dimension: **512**.
+
+| File | Contents |
+|---|---|
+| `backbone.pt` | Backbone for embeddings and downstream tasks. |
+| `pretraining.pt` | Backbone, pretraining objective heads, and EMA target encoder; optimizer and scheduler states are excluded. |
+
+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 +1,2 @@
+0ed7a78abb862e9cf7fdbc4d167209014753c440226f5871bc06f8f3e72e6fae  backbone.pt
+895db92ecb38d4f505185e7e5c5f55f60caba8dd75ef6ec04b781a7ec3440795  pretraining.pt

backbone.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ed7a78abb862e9cf7fdbc4d167209014753c440226f5871bc06f8f3e72e6fae
+size 161189967

manifest.json

@@ -0,0 +1,43 @@
+{
+  "schema_version": 1,
+  "model_name": "PoreFM-RNA",
+  "model_version": "0.1.0",
+  "embedding_dim": 512,
+  "chemistry": "rna004",
+  "molecule_type": "rna",
+  "artifacts": [
+    {
+      "file": "backbone.pt",
+      "size_bytes": 161189967,
+      "file_sha256": "0ed7a78abb862e9cf7fdbc4d167209014753c440226f5871bc06f8f3e72e6fae",
+      "role": "backbone",
+      "format": "pytorch_checkpoint",
+      "tensor_fingerprint": {
+        "scheme": "porefm-tensor-content-v1",
+        "sha256": "6803fba493ba4c00f0eedec76a51315b250e0c7f3864763836e2640f46c47875"
+      }
+    },
+    {
+      "file": "pretraining.pt",
+      "size_bytes": 204601699,
+      "file_sha256": "895db92ecb38d4f505185e7e5c5f55f60caba8dd75ef6ec04b781a7ec3440795",
+      "role": "pretraining",
+      "format": "pytorch_checkpoint",
+      "tensor_fingerprint": {
+        "scheme": "porefm-tensor-content-v1",
+        "sha256": "0a5b07538df3ec75774a37d08f04b28292487081a29b68e389b1644963d8abd6"
+      }
+    }
+  ],
+  "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."
+    ]
+  }
+}

pretraining.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:895db92ecb38d4f505185e7e5c5f55f60caba8dd75ef6ec04b781a7ec3440795
+size 204601699