Upload 6 files

README.md

@@ -1,3 +1,59 @@
----
-license: cc-by-4.0
----
+---
+license: cc-by-4.0
+pipeline_tag: time-series-forecasting
+datasets:
+- williamgilpin/dysts
+---
+
+# DynaMix
+
+[![arXiv](https://img.shields.io/badge/arXiv-2505.13192-b31b1b.svg)](https://arxiv.org/abs/2505.13192)
+
+DynaMix is a foundation model for zero-shot inference of dynamical systems that preserves long-term statistics. Unlike traditional approaches that require retraining for each new system, DynaMix provides context driven generalization to unseen dynamical systems.
+
+- **Accurate Zero-Shot Dynamical Systems Reconstruction**: DynaMix generalizes across diverse dynamical systems without fine-tuning, accurately capturing attractor geometry and long-term statistics.
+- **Context Felxible Dynamics Modeling**: The multivariate architecture captures dependencies across system dimensions and adapts to different dimensionalities and context lengths.
+- **Efficient and Lightweight**: Designed to be efficient with a few thousand parameters, DynaMix can also run on CPU for inference, and is enabling orders-of-magnitude faster inference than traditional foundation models.
+- **General Time Series Forecasting**: Extends beyond DSR to general time series forecasting using adaptable embedding techniques.
+
+For complete documentation and code, visit the [DynaMix repository](https://github.com/yourusername/zero-shot-DSR).
+
+## Model Description
+
+DynaMix is based on a mixture of experts (MoE) architecture operating in latent space:
+
+1. **Expert Networks**: Each expert is a specialized dynamical model, given trhough RNN based architectures
+
+2. **Gating Network**: Selects experts based on the provided context and current latent representation of the dynamics
+
+By aggregating the expert weighting with the expert prediction the next state is predicted.
+
+## Usage
+
+To load the model in python using the corresponding codebase [DynaMix repository](https://github.com/yourusername/zero-shot-DSR), use:
+
+```python
+from src.utilities.utilities import load_hf_model
+
+# Initialize model with architecture
+model = load_hf_model(model_name="dynamix-3d-alrnn-v1.0")
+```
+
+Given context data from the target system with shape (`T_C`, `S`, `N`) (where `T_C` is the context length, `S` the number of sequences that should get processed and `N` the data dimensionality), generate forecasts by passing the data through the `DynaMixForecaster` along with the loaded model. Further details can be found in the GitHub repository [DynaMix repository](https://github.com/yourusername/zero-shot-DSR).
+
+
+## Citation
+
+If you use DynaMix in your research, please cite our paper:
+
+```
+@misc{hemmer2025truezeroshotinferencedynamical,
+title={True Zero-Shot Inference of Dynamical Systems Preserving Long-Term Statistics},
+author={Christoph Jürgen Hemmer and Daniel Durstewitz},
+year={2025},
+eprint={2505.13192},
+archivePrefix={arXiv},
+primaryClass={cs.LG},
+url={https://arxiv.org/abs/2505.13192},
+}
+```

config_3d-alrnn-v1.0.json

@@ -0,0 +1,20 @@
+{
+  "model_type": "dynamix",
+  "model_name": "dynamix-3d-alrnn-v1.0",
+  "architecture": {
+    "M": 30,
+    "N": 3,
+    "Experts": 10,
+    "P": 2,
+    "hidden_dim": 50,
+    "expert_type": "almost_linear_rnn",
+    "probabilistic_expert": false
+  },
+  "metadata": {
+    "context_dimensions": 3,
+    "context_length": "variable",
+    "author": "Christoph Hemmer",
+    "paper": "https://arxiv.org/abs/2505.13192",
+    "license": "cc-by-4.0"
+  }
+}

config_6d-alrnn-v1.0.json

@@ -0,0 +1,20 @@
+{
+  "model_type": "dynamix",
+  "model_name": "dynamix-6d-alrnn-v1.0",
+  "architecture": {
+    "M": 10,
+    "N": 6,
+    "Experts": 80,
+    "P": 2,
+    "hidden_dim": 50,
+    "expert_type": "almost_linear_rnn",
+    "probabilistic_expert": false
+  },
+  "metadata": {
+    "context_dimensions": 6,
+    "context_length": "variable",
+    "author": "Christoph Hemmer",
+    "paper": "https://arxiv.org/abs/2505.13192",
+    "license": "cc-by-4.0"
+  }
+}

dynamix-3d-alrnn-v1.0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c950aef03f24e600bb159a05bf64aaea0fc89a6c66310baac624ac4b7e10ed5b
+size 44152

dynamix-6d-alrnn-v1.0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a10dc3de0f8e1f98b42f61dc9d728e51176b6ae67b94d08b2f5dd9d82a6d2e71
+size 89136

model_index.json

@@ -0,0 +1,13 @@
+{
+  "variants": {
+    "3d-alrnn": {
+      "config": "config_3d-alrnn-v1.0.json",
+      "weights": "dynamix-3d-alrnn-v1.0.safetensors"
+    },
+    "6d-alrnn": {
+      "config": "config_6d-alrnn-v1.0.json",
+      "weights": "dynamix-6d-alrnn-v1.0.safetensors"
+    }
+  },
+  "architecture": "dynamix"
+}