Add NotaGen-X safetensors mirror (MIT, from ElectricAlexis/NotaGen)

README.md

@@ -0,0 +1,69 @@
+---
+license: mit
+library_name: pytorch
+tags:
+  - music-generation
+  - symbolic-music
+  - abc-notation
+  - classical
+  - transformer
+pipeline_tag: text-to-audio
+---
+
+# NotaGen-X — MAESTRO Mirror
+
+Safetensors mirror of the NotaGen-X model weights, used by
+[MAESTRO](https://github.com/AEmotionStudio) for the AI-Workstation "Create →
+NotaGen" model card.
+
+This repository ships **only the model weights** (no optimizer state) in the
+[safetensors](https://github.com/huggingface/safetensors) format, so they load
+into MAESTRO without arbitrary-code execution risk. The original upstream
+checkpoints from `ElectricAlexis/NotaGen` are PyTorch `.pth` files bundling
+optimizer state, epoch counters, etc.
+
+## Files
+
+| File | Purpose |
+| --- | --- |
+| `model.safetensors` | NotaGen-X model state dict (516 M params, fp32, ~1.92 GB) |
+| `config.json` | Architecture hyperparameters consumed by NotaGen's loader |
+| `README.md` | This file |
+
+## Provenance
+
+* Upstream:
+  [`ElectricAlexis/NotaGen`](https://huggingface.co/ElectricAlexis/NotaGen)
+  · file `weights_notagenx_p_size_16_p_length_1024_p_layers_20_h_size_1280.pth`
+* Conversion: `torch.load(...)['model']` → contiguous CPU tensors →
+  `safetensors.torch.save_file(...)`. Round-trip verified (zero mismatches over
+  all 323 tensors).
+* Training metadata preserved in safetensors header
+  (`epoch`, `best_epoch`, `min_eval_loss`).
+
+## Architecture
+
+Hierarchical Tunesformer (GPT-2 backbone) generating ABC notation:
+
+* `p_size = 16`  (patch size)
+* `p_length = 1024`  (patch sequence length)
+* `p_layers = 20`  (patch-level decoder layers)
+* `c_layers = 6`   (character-level decoder layers)
+* `h_size = 1280`  (hidden size)
+
+## Loading
+
+```python
+from safetensors.torch import load_file
+state = load_file("model.safetensors")
+# Pass to NotaGen's model class — same key layout as the upstream `.pth`'s
+# `["model"]` sub-dict.
+```
+
+MAESTRO's loader (`backend/ai/models/notagen.py`) handles this automatically and,
+if the upstream NotaGen inference script demands a `.pth` on disk, materialises
+one alongside the safetensors on first load.
+
+## License
+
+MIT, inherited from upstream NotaGen.

config.json

@@ -0,0 +1,17 @@
+{
+  "model_type": "notagen",
+  "variant": "notagen-x",
+  "patch_size": 16,
+  "patch_length": 1024,
+  "patch_layers": 20,
+  "char_layers": 6,
+  "hidden_size": 1280,
+  "framework": "pytorch",
+  "format": "safetensors",
+  "param_count": 515902720,
+  "dtype": "float32",
+  "source": {
+    "repo": "ElectricAlexis/NotaGen",
+    "file": "weights_notagenx_p_size_16_p_length_1024_p_layers_20_h_size_1280.pth"
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d531d3ec4d191e3448db2315e0d4bfaee222310818a8a71d681984416d33a7b
+size 2063649720