Upload fm_tutorial Sudoku checkpoints

README.md

@@ -0,0 +1,12 @@
+# fm-tutorial assets
+
+Pretrained Sudoku checkpoints for [fm_tutorial notebook 05](https://github.com/JChemseddine/fm_tutorial/blob/main/notebooks/05_continuous_discrete_sudoku.ipynb).
+
+Three 28M-parameter DiT checkpoints on *Sudoku Extreme*:
+- `vmf_d11_p1/checkpoint.pt` — spherical flow matching (vMF), no time conditioning
+- `vmf_tc_d11_p1/checkpoint.pt` — same, with time conditioning
+- `masked_p1/checkpoint.pt` — masked diffusion baseline (MDLM-style)
+
+Each `.pt` is a torch.save dict with keys `model_state_dict`, `ema_state_dict`, `config`, `step`, and (for vmf) `warp_state`.
+
+Source: *Spherical Flows for Sampling Discrete Distributions* ([arXiv:2605.05629](https://arxiv.org/abs/2605.05629)).

masked_p1/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3dd461e0cdb2377a28c8907b56eac9fd4846edb5c2573a434a5a81a5f898b87
+size 457061307

vmf_d11_p1/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f62674593c6b47ca6b07494ae75daf7654588de563096a0c9eccecf73bed6735
+size 457088419

vmf_tc_d11_p1/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d46747439a0f64e60f2b7d0adfba3e88f4f16dbbcdbb13de9a6dbb347445a26d
+size 457088483