| --- |
| title: README |
| emoji: 馃尨 |
| colorFrom: green |
| colorTo: yellow |
| sdk: static |
| app_file: home.html |
| pinned: false |
| short_description: Jamaica's independent AI research lab. |
| --- |
| |
| <img src="https://huggingface.co/spaces/CorxLabs/README/resolve/main/banner-site.png" alt="CorX Labs. Architecting the future, from the ground up." width="100%"> |
|
|
| **CorX Labs is Jamaica's independent AI research lab.** We build Jamaican AI from the ground up: five open models so |
| far, from CorX3.8, a 27-billion-parameter Jamaican Patois assistant, to NatureV1, a weather and hurricane model. Most |
| were trained from random weights on a single GPU, and where one is a fine-tune, we say so. |
|
|
| | Models built | Released with weights | Technical reports | Licence | |
| |:-:|:-:|:-:|:-:| |
| | **5** | **4** | **5** | **Apache-2.0** | |
|
|
| <img src="https://huggingface.co/spaces/CorxLabs/README/resolve/main/rule.png" width="100%" height="4" alt=""> |
|
|
| ### Models |
|
|
| | Model | What it is | Size | Built from | Report | |
| |---|---|:-:|---|:-:| |
| | [**CorX3.8-27B**](https://huggingface.co/CorxLabs/CorX3.8-27B) | Jamaican Patois conversational assistant. Patois by default, English on request. | 27B | Fine-tune of Qwen3.8-27B, fully merged | [03](https://corxlabs-papers.static.hf.space/corx3.8-27b-model-report.html) | |
| | [**CorX1.5**](https://huggingface.co/CorxLabs/CorX1.5-160M) | Decoder-only language model with learned role embeddings | 157.8M | From scratch, tokenizer included | [01](https://corxlabs-papers.static.hf.space/corx1.5-technical-report.html) | |
| | [**TriStream-SVS**](https://huggingface.co/CorxLabs/TriStream-SVS-300M) | Singing-voice synthesis: pitch, timbre and breath in three separate streams | 321.8M | From scratch | [02](https://corxlabs-papers.static.hf.space/tristream-svs-technical-report.html) | |
| | [**NatureV1**](https://huggingface.co/CorxLabs/NatureV1-500) | Probabilistic weather and hurricane model, attention in kilometres on the sphere | 89.45M | From scratch, on the iHELIX engine | [05](https://corxlabs-papers.static.hf.space/naturev1-hurricane-physics-report.html) | |
| | [**HELIX**](https://pypi.org/project/helix-lm/) | Linear-scaling sequence architecture that keeps exact long-range recall | configurable | From scratch; no trained checkpoints | [04](https://corxlabs-papers.static.hf.space/helix-technical-report.html) | |
|
|
| Browse by collection: [Text](https://huggingface.co/collections/CorxLabs/text-models-6ad400811d7073d767ebe7f1) 路 |
| [Singing voice](https://huggingface.co/collections/CorxLabs/svs-models-6ad40082a6e143550bd7aaa6) 路 |
| [Weather](https://huggingface.co/collections/CorxLabs/weather-models-6ad40082a150e48c970f176a) |
|
|
| ### Papers |
|
|
| Read them on the web or download the PDFs: **[CorX Labs Papers](https://huggingface.co/spaces/CorxLabs/papers)** |
|
|
| <table> |
| <tr> |
| <td align="center" width="20%"><a href="https://corxlabs-papers.static.hf.space/corx1.5-technical-report.html"><img src="https://huggingface.co/spaces/CorxLabs/README/resolve/main/papers/corx1.5-technical-report.png" alt="CorX1.5 technical report"></a></td> |
| <td align="center" width="20%"><a href="https://corxlabs-papers.static.hf.space/tristream-svs-technical-report.html"><img src="https://huggingface.co/spaces/CorxLabs/README/resolve/main/papers/tristream-svs-technical-report.png" alt="TriStream-SVS technical report"></a></td> |
| <td align="center" width="20%"><a href="https://corxlabs-papers.static.hf.space/corx3.8-27b-model-report.html"><img src="https://huggingface.co/spaces/CorxLabs/README/resolve/main/papers/corx3.8-27b-model-report.png" alt="CorX3.8-27B model report"></a></td> |
| <td align="center" width="20%"><a href="https://corxlabs-papers.static.hf.space/helix-technical-report.html"><img src="https://huggingface.co/spaces/CorxLabs/README/resolve/main/papers/helix-technical-report.png" alt="HELIX technical report"></a></td> |
| <td align="center" width="20%"><a href="https://corxlabs-papers.static.hf.space/naturev1-hurricane-physics-report.html"><img src="https://huggingface.co/spaces/CorxLabs/README/resolve/main/papers/naturev1-hurricane-physics-report.png" alt="NatureV1 hurricane physics report"></a></td> |
| </tr> |
| </table> |
|
|
| 1. **[CorX1.5: a 158M-parameter language model trained from random weights on one GPU.](https://corxlabs-papers.static.hf.space/corx1.5-technical-report.html)** ([PDF](https://corxlabs-papers.static.hf.space/corx1.5-technical-report.pdf)) The architecture, the |
| three-stage training, and the memory arithmetic that fits three billion tokens through one card. |
| 2. **[TriStream-SVS: building the source-filter model of the voice into a singing synthesiser.](https://corxlabs-papers.static.hf.space/tristream-svs-technical-report.html)** ([PDF](https://corxlabs-papers.static.hf.space/tristream-svs-technical-report.pdf)) Three streams that |
| cannot share information until a late fusion trunk, with zero-shot cloning and a 32-step flow-matching decoder. |
| 3. **[CorX3.8-27B: giving an open 27B model a Jamaican voice.](https://corxlabs-papers.static.hf.space/corx3.8-27b-model-report.html)** ([PDF](https://corxlabs-papers.static.hf.space/corx3.8-27b-model-report.pdf)) What a rank-64 LoRA on 19 million tokens changed, and |
| what it did not. |
| 4. **[HELIX: separating memory capacity from bandwidth in a linear-scaling sequence model.](https://corxlabs-papers.static.hf.space/helix-technical-report.html)** ([PDF](https://corxlabs-papers.static.hf.space/helix-technical-report.pdf)) N<sup>1.00</sup> attention |
| pairs, and recall that ties full attention while the same model without its index falls to chance. |
| 5. **[Hurricane tracks without a neural network.](https://corxlabs-papers.static.hf.space/naturev1-hurricane-physics-report.html)** ([PDF](https://corxlabs-papers.static.hf.space/naturev1-hurricane-physics-report.pdf)) A physics consensus that beats extrapolation and CLIPER at every lead |
| on 4,447 forecasts from four seasons it never saw. |
|
|
| ### Measured, not promised |
|
|
| | Hurricane track error (km), 2018 and 2020-2022, all basins | 24 h | 48 h | 72 h | 120 h | |
| |---|:-:|:-:|:-:|:-:| |
| | Straight-line extrapolation (strongest per lead) | 179 | 442 | 751 | 1,417 | |
| | CLIPER | 163 | 378 | 589 | 914 | |
| | **NatureV1 hurricane physics, no neural network** | **127** | **301** | **515** | **884** | |
|
|
| Global AI models such as GraphCast and Pangu-Weather remain far better beyond 12 hours, and the report says so. The |
| same rule runs through every model here: results are measured on data the model never trained on, "trained from |
| scratch", "fine-tuned" and "not trained yet" are kept apart, and nothing is claimed that has not been measured. |
| TriStream-SVS, for example, has no listening tests yet, so it reports no quality scores. |
|
|
| <img src="https://huggingface.co/spaces/CorxLabs/README/resolve/main/rule.png" width="100%" height="4" alt=""> |
|
|
| [corx-labs.com](https://www.corx-labs.com/) 路 [Chat with CorX3.8](https://www.corx-labs.com/chat/) 路 |
| [Documentation](https://www.corx-labs.com/documentation/) 路 [Blog](https://www.corx-labs.com/blog/) 路 |
| [Benchmarks](https://www.corx-labs.com/benchmarks/) 路 PyPI: [naturev1](https://pypi.org/project/naturev1/), |
| [ihelix](https://pypi.org/project/ihelix/), [helix-lm](https://pypi.org/project/helix-lm/) |
|
|
| <sub>CorX Labs 路 Westmoreland, Jamaica 路 Architecting the future, from the ground up.</sub> |
|
|
