Release SanSi (seed 0): LoRA adapter, readouts and model card

README.md

@@ -0,0 +1,149 @@
+---
+license: apache-2.0
+language:
+- en
+library_name: peft
+base_model: ByteDance/Ouro-1.4B
+tags:
+- looped-language-model
+- typed-decision
+- calibration
+- lora
+---
+
+# SanSi
+
+<p align="center">
+  <a href="https://minnesotanlp.github.io/Sansi/"><img src="https://img.shields.io/badge/Website-Project%20Page-1E90FF.svg?logo=googlechrome&logoColor=white" alt="Project page"/></a>
+  <a href="https://arxiv.org/abs/2610.07730"><img src="https://img.shields.io/badge/arXiv-2610.07730-B31B1B.svg?logo=arxiv&logoColor=white" alt="arXiv"/></a>
+  <a href="https://github.com/minnesotanlp/Sansi"><img src="https://img.shields.io/badge/GitHub-Code-181717.svg?logo=github" alt="Code"/></a>
+  <a href="https://huggingface.co/minnesotanlp/SanSi-2.6B"><img src="https://img.shields.io/badge/-SanSi--2.6B-FFD21E?logo=huggingface&logoColor=black" alt="SanSi-2.6B"/></a>
+  <a href="https://www.apache.org/licenses/LICENSE-2.0"><img src="https://img.shields.io/badge/License-Apache%202.0-blue.svg" alt="Apache 2.0"/></a>
+</p>
+
+SanSi is the model of the paper [SanSi: A Looped Typed Decision Model for System 1.5 Thinking](https://arxiv.org/abs/2610.07730).
+It is a typed decision model: given a text (the state), a question and 2 to 26 declared options, it returns a
+probability for each option, without generating text. It is built on
+[Ouro-1.4B](https://huggingface.co/ByteDance/Ouro-1.4B), a language model pre-trained to loop: one stack of 24 shared
+layers is applied T = 8 times. The option probabilities are read after every loop, so one forward pass gives the
+decision at every budget from one loop to eight.
+
+This repository holds what was trained: LoRA adapters of rank 64 and one small readout per loop, 60.8M parameters.
+The backbone stays frozen; it is downloaded from `ByteDance/Ouro-1.4B` at the revision the model was trained on.
+
+| Model | Backbone | Trained parameters | Accuracy after loop 8 |
+|---|---|---:|---:|
+| **SanSi** (this model) | Ouro-1.4B | 60.8M | 72.0 |
+| [SanSi-2.6B](https://huggingface.co/minnesotanlp/SanSi-2.6B) | Ouro-2.6B | 121.4M | 75.8 |
+
+Accuracy (%) on the 10,027 test items of the paper, mean of three training seeds.
+
+## How to use
+
+The loading code is in the [GitHub repository](https://github.com/minnesotanlp/Sansi). Use a GPU; the backbone runs
+in bfloat16.
+
+```bash
+git clone https://github.com/minnesotanlp/Sansi
+cd Sansi
+pip install -r requirements.txt
+```
+
+```python
+from sansi.hub import load, decide
+
+model, tok = load("minnesotanlp/SanSi")   # this adapter, and Ouro-1.4B at its pinned revision
+
+probs = decide(
+    model, tok,
+    state="Mia is taller than Sam. Sam is taller than Lee.",
+    question="Who is the shortest?",
+    options=["Mia", "Sam", "Lee"],
+)
+print(probs[0])    # after loop 1, at an eighth of the computation: about [0.02, 0.07, 0.91]
+print(probs[-1])   # after loop 8: about [0.00, 0.00, 1.00]
+```
+
+`decide` returns one list per loop, each with one probability per option in the order given. It writes the prompt
+the model was trained on,
+
+```
+<state>
+
+Question: <question>
+Options: (A) <option 1> (B) <option 2> ...
+Answer:
+```
+
+and reads the option letters at its last token after every loop. `decide(..., loops=4)` runs four loops only, at half
+the computation (71.6% instead of 72.0% on the test items). To run a whole dataset, use `eval/evaluate.py` of the
+repository. An item whose answer the state does not give was trained towards the uniform distribution: a low top
+probability means that the model does not commit to an answer (the paper counts a hard answer when the top
+probability reaches (1 + 1/K) / 2 for K options).
+
+## Results
+
+Accuracy (%) on the 10,027 test items after every loop: the mean of the three training seeds of the paper, and this
+checkpoint (seed 0).
+
+| Loop | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 |
+|---|---:|---:|---:|---:|---:|---:|---:|---:|
+| Mean of three seeds | 58.4 | 66.9 | 70.4 | 71.6 | 71.9 | 72.1 | 72.1 | 72.0 |
+| This checkpoint (seed 0) | 57.7 | 67.2 | 70.4 | 71.2 | 71.2 | 71.4 | 71.4 | 71.3 |
+
+The main comparison of the paper: all models are trained on the same data, with the same recipe except Kev-4B (our
+data), which uses Kev's code; mean of three seeds. In-distribution items come from the training sources, near
+transfer from harder or reworded versions of them, far transfer from sources never trained on. Cost is the GPU time
+of one pass over the test items, with one loop of Ouro-1.4B as 1.
+
+| Model | Params | Loops | Cost | All | In-dist. | Near | Far | ECE |
+|---|---:|---:|---:|---:|---:|---:|---:|---:|
+| SmolLM2-1.7B | 1.7B | 1 | 1.1 | 58.4 | 76.1 | 57.7 | 52.3 | 0.069 |
+| Ouro-1.4B, one loop | 1.4B | 1 | 1.0 | 58.6 | 77.3 | 59.9 | 51.3 | 0.137 |
+| Qwen3.5-2B | 1.9B | 1 | 1.2 | 66.7 | 84.3 | 62.3 | 61.7 | 0.123 |
+| Qwen3.5-4B | 4.2B | 1 | 2.4 | 73.8 | 88.5 | 68.9 | 70.1 | 0.113 |
+| Kev-4B (our data) | 4.2B | 1 | 2.1 | 74.3 | 88.6 | 70.9 | 70.3 | 0.119 |
+| **SanSi** | 1.4B | 8 | 7.7 | 72.0 | 86.6 | 67.7 | 68.0 | 0.093 |
+| SanSi-2.6B | 2.7B | 8 | 14.8 | 75.8 | 88.4 | 74.4 | 71.6 | 0.078 |
+
+## Training
+
+- Data: the 12,800 training items of the paper's decision suite, from 20 public sources. The GitHub repository
+  downloads the sources at fixed revisions and rebuilds the dataset byte for byte (`data.download_raw`,
+  `data.build_main`, `data.verify`).
+- Model: Ouro-1.4B frozen; LoRA of rank 64 (alpha 128, dropout 0.05) on the attention and MLP projections; one
+  readout of rank 16 per loop.
+- Loss at every loop: the cross-entropy plus the Brier score against the item's target distribution.
+- 1,000 steps of 16 items; AdamW with learning rates 1e-4 (LoRA) and 1e-3 (readout), 200 warm-up steps, cosine
+  decay to 10%, gradient clipping at 1.0; two RTX A6000 GPUs; seed 0.
+
+```bash
+python -m train.train --model <Ouro-1.4B> --loops 8 --seed 0 --out runs/sansi_s0
+```
+
+## Limitations
+
+- English only. The model answers one question with 2 to 26 declared options per call, in the prompt format above.
+- Running more loops than the eight it was trained with lowers accuracy.
+- This is one training seed; the test accuracy of the three seeds of the paper has a standard deviation of 0.7 points.
+- Looping does not replace parameters entirely: Qwen3.5-4B, with three times the parameters, is 1.8 points more
+  accurate, at a third of the computation.
+
+## License
+
+The adapter and the readouts are released under the Apache 2.0 license, as are the code and the backbone Ouro-1.4B.
+The training data comes from public datasets that keep their own licenses (`data/README.md` of the repository).
+
+## Citation
+
+```bibtex
+@misc{gan2026sansiloopedtypeddecision,
+      title={SanSi: A Looped Typed Decision Model for System 1.5 Thinking},
+      author={Shuyu Gan and Young-Jun Lee and Dongyeop Kang},
+      year={2026},
+      eprint={2610.07730},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2610.07730},
+}
+```

adapter_config.json

@@ -0,0 +1,54 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "OuroForCausalLM",
+    "parent_library": "transformers_modules.Ouro_hyphen_1_dot_4B.modeling_ouro"
+  },
+  "base_model_name_or_path": "ByteDance/Ouro-1.4B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": "574fa66cb8bf5abdc979642d01cf2b79b16bfab1",
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a0a15b2a99e44c994d7aad440722606e16518c726f08ff959809e2c1c98ccb
+size 242266152

readout.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51c2b3986441aa96bb9c1789ffe141529d63bc4ab92cc5bea768eb72737a1cf3
+size 1062196

sansi_config.json

@@ -0,0 +1,11 @@
+{
+ "backbone": "ByteDance/Ouro-1.4B",
+ "backbone_revision": "574fa66cb8bf5abdc979642d01cf2b79b16bfab1",
+ "loops": 8,
+ "n_loop_params": 8,
+ "readout_rank": 16,
+ "seed": 0,
+ "training_steps": 1000,
+ "paper": "https://arxiv.org/abs/2610.07730",
+ "code": "https://github.com/minnesotanlp/Sansi"
+}