Upload folder using huggingface_hub

README.md

@@ -0,0 +1,74 @@
+---
+library_name: sigs
+license: mit
+datasets:
+  - oroikono/sigs-symbolic-pde-corpus
+arxiv: 2502.01476
+tags:
+  - transformers
+  - pytorch
+  - scientific-machine-learning
+  - neuro-symbolic-ai
+  - symbolic-regression
+  - pde
+---
+
+# SIGS ICML 2026 Grammar-VAE
+
+This repository contains the grammar variational autoencoder used by SIGS,
+**Neuro-Symbolic AI for Analytical Solutions of Differential Equations**
+(Oikonomou et al., ICML 2026).
+
+## Model description
+
+SIGS embeds syntactically valid mathematical expressions into a continuous
+latent space and decodes latent vectors under a context-free grammar. The wider
+SIGS pipeline searches that space for closed-form candidates and then refines
+their constants against differential-equation residuals.
+
+This is a grammar model, not a natural-language model. Its inputs are one-hot
+grammar-production sequences with shape `[batch, productions, sequence_length]`.
+
+## Loading
+
+Install SIGS with its Hugging Face dependencies, then load the checkpoint:
+
+```python
+from sigs.huggingface import SIGSModel
+
+model = SIGSModel.from_pretrained("oroikono/sigs-icml-2026")
+```
+
+The associated production-sequence corpus can be represented with Hugging Face
+Datasets, and `examples/train_with_accelerate.py` provides a distributed training
+entry point.
+
+## Intended use
+
+- Research on grammar-guided symbolic generation.
+- Reproducing the symbolic proposal component of SIGS.
+- Closed-form differential-equation solution discovery with the wider SIGS
+  search and residual-refinement pipeline.
+
+## Limitations
+
+- Generated candidates are restricted to the published grammar and maximum
+  production-sequence length.
+- The model alone does not certify that an expression solves a differential
+  equation; residual, initial-condition, and boundary-condition checks remain
+  necessary.
+- Performance outside the PDE families and expression corpus reported in the
+  paper has not been established.
+
+## Citation
+
+```bibtex
+@misc{oikonomou2026neurosymbolic,
+  title={Neuro-Symbolic AI for Analytical Solutions of Differential Equations},
+  author={Oikonomou, Orestis and Lingsch, Levi and Grund, Dana and Mishra, Siddhartha and Kissas, Georgios},
+  year={2026},
+  eprint={2502.01476},
+  archivePrefix={arXiv},
+  primaryClass={cs.LG}
+}
+```

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "SIGSModel"
+  ],
+  "decoder_dropout": 0.0,
+  "decoder_hidden_size": 512,
+  "decoder_mode": "positional",
+  "decoder_num_layers": 1,
+  "decoder_rnn_type": "gru",
+  "decoder_samples": 1,
+  "dtype": "float32",
+  "encoder_conv_sizes": [
+    64,
+    128,
+    256
+  ],
+  "encoder_dropout": 0.0,
+  "encoder_hidden_size": 256,
+  "encoder_kernel_sizes": [
+    2,
+    3,
+    4
+  ],
+  "encoder_layer_norm": false,
+  "kl_weight": 1.0,
+  "latent_size": 32,
+  "model_type": "sigs",
+  "sequence_length": 72,
+  "tightness": 1.0,
+  "transformers_version": "5.15.0",
+  "vocab_size": 53
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c80c59384a6bfe70d5c7cd452a633098d273bac260af0452baa5c4883bbe9aee
+size 24495888