|
|
--- |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- geofractal-router |
|
|
- collective-intelligence |
|
|
- math-reasoning |
|
|
- multi-stream |
|
|
- emergence |
|
|
- routing |
|
|
datasets: |
|
|
- openai/gsm8k |
|
|
base_model: |
|
|
- tbs17/MathBERT |
|
|
- google-t5/t5-base |
|
|
pipeline_tag: text-classification |
|
|
--- |
|
|
|
|
|
# V2 first epoch ready |
|
|
Looking much stronger. |
|
|
|
|
|
 |
|
|
|
|
|
|
|
|
# V1 BAD END - V2 using qwen 2.5 math 1.5b |
|
|
Will the Qwen 2.5 1.5b model cut through the noise? |
|
|
|
|
|
|
|
|
``` |
|
|
====================================================================== |
|
|
GALAXY BRAIN COLLECTIVE - GSM8K FINAL RESULTS |
|
|
====================================================================== |
|
|
|
|
|
Streams: |
|
|
FUZZY: MathBERT (symbolic), T5 (linguistic) |
|
|
DETERMINISTIC: Eigenspectrum, Cayley-Menger, Symbolic Calc, Fractal |
|
|
|
|
|
| Epoch | Collective | MathBERT | T5 | Eigen | Cayley | Symbolic | Fractal | Ο | |
|
|
|-------|------------|----------|-----|-------|--------|----------|---------|-------| |
|
|
| 1 | 8.9% | 10.4% | 13.0% | 5.4% | 5.4% | 5.7% | 6.7% | 0.686 | |
|
|
| 2 | 9.6% | 8.9% | 13.0% | 6.5% | 6.5% | 4.6% | 6.1% | 0.738 | |
|
|
| 3 | 9.9% | 9.6% | 13.6% | 5.8% | 5.8% | 4.5% | 5.8% | 0.728 | |
|
|
| 4 | 8.3% | 10.1% | 13.3% | 6.1% | 4.5% | 4.8% | 4.5% | 0.619 | |
|
|
| 5 | 9.0% | 11.1% | 14.6% | 4.5% | 4.6% | 5.0% | 5.9% | 0.620 | |
|
|
|
|
|
β Best epoch: 3 with collective accuracy 9.9% |
|
|
β All checkpoints available at: https://huggingface.co/AbstractPhil/math_collective |
|
|
``` |
|
|
|
|
|
# Math Collective - Galaxy Brain Router |
|
|
|
|
|
**6-stream collective intelligence system for mathematical reasoning.** |
|
|
|
|
|
## Architecture |
|
|
``` |
|
|
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ |
|
|
β GALAXY BRAIN COLLECTIVE β |
|
|
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ€ |
|
|
β FUZZY STREAMS (learned representations) β |
|
|
β βββ MathBERT (frozen) β Head A β "symbolic understanding" β |
|
|
β βββ T5-base (frozen) β Head B β "linguistic reasoning" β |
|
|
β β |
|
|
β DETERMINISTIC STREAMS (pure computation) β |
|
|
β βββ Eigenspectrum β Head C β "covariance geometry" β |
|
|
β βββ Cayley-Menger β Head D β "distance geometry" β |
|
|
β βββ Symbolic Calc β Head E β "actual arithmetic" β |
|
|
β βββ Fractal Dim β Head F β "complexity measure" β |
|
|
β β |
|
|
β All 6 streams β Fusion β Classifier β |
|
|
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ |
|
|
``` |
|
|
|
|
|
## Key Innovation |
|
|
|
|
|
**Fuzzy + Deterministic Routing** |
|
|
|
|
|
The router learns WHEN to trust each stream: |
|
|
- Simple arithmetic? Trust the Symbolic Calculator (deterministic) |
|
|
- Complex word problem? Trust MathBERT/T5 (semantic) |
|
|
- Ambiguous? Triangulate across all 6 perspectives |
|
|
|
|
|
## Streams |
|
|
|
|
|
| Stream | Type | Source | Purpose | |
|
|
|--------|------|--------|---------| |
|
|
| MathBERT | Fuzzy | tbs17/MathBERT (frozen) | Mathematical notation understanding | |
|
|
| T5-base | Fuzzy | t5-base (frozen) | General language reasoning | |
|
|
| Eigenspectrum | Deterministic | Covariance eigenvalues | Geometric structure of embeddings | |
|
|
| Cayley-Menger | Deterministic | Distance matrix geometry | Simplex volume features | |
|
|
| Symbolic | Deterministic | Regex + arithmetic | Actual number extraction & computation | |
|
|
| Fractal | Deterministic | Correlation dimension | Problem complexity measure | |
|
|
|
|
|
## Training |
|
|
|
|
|
- **Dataset**: GSM8K (Grade School Math 8K) |
|
|
- **Task**: Answer magnitude bucket prediction (20 buckets) |
|
|
- **Frozen params**: ~330M (MathBERT + T5) |
|
|
- **Trainable params**: ~15M (routing heads, fusion, projections) |
|
|
|
|
|
## Emergence Metric (Ο) |
|
|
``` |
|
|
Ο = collective_accuracy / max(individual_accuracies) |
|
|
|
|
|
Ο > 1.0 = emergence (collective outperforms best individual) |
|
|
``` |
|
|
|
|
|
## Usage |
|
|
```python |
|
|
from huggingface_hub import hf_hub_download |
|
|
import torch |
|
|
|
|
|
# Download checkpoint |
|
|
checkpoint_path = hf_hub_download( |
|
|
repo_id="AbstractPhil/math_collective", |
|
|
filename="checkpoints/checkpoint_epoch_5.pt" |
|
|
) |
|
|
|
|
|
# Load and use (see geofractal-router for full implementation) |
|
|
checkpoint = torch.load(checkpoint_path) |
|
|
print(f"Epoch: {checkpoint['epoch']}") |
|
|
print(f"Metrics: {checkpoint['metrics']}") |
|
|
``` |
|
|
|
|
|
## Related |
|
|
|
|
|
- **Framework**: [AbstractPhil/geofractal_router](https://huggingface.co/AbstractPhil/geofractal_router) |
|
|
- **Paper**: Coming soon |
|
|
- **Code**: [GitHub - geofractal](https://github.com/AbstractEyes/geofractal) |
|
|
|
|
|
## Citation |
|
|
```bibtex |
|
|
@misc{abstractphil2025mathcollective, |
|
|
title={Math Collective: Galaxy Brain Routing for Mathematical Reasoning}, |
|
|
author={AbstractPhil}, |
|
|
year={2025}, |
|
|
publisher={Hugging Face}, |
|
|
url={https://huggingface.co/AbstractPhil/math_collective} |
|
|
} |
|
|
``` |
|
|
|
|
|
## License |
|
|
|
|
|
Apache 2.0 |
|
|
|