Spaces:
Running on Zero
Running on Zero
|
Download README.md from robtacconelli/Nacrith-GPU: direct link, hf CLI and curl.
- Browser
- Download file 902 Bytes
-
https://huggingface.co/spaces/robtacconelli/Nacrith-GPU/resolve/main/README.md
- Command line
-
hf download hf://spaces/robtacconelli/Nacrith-GPU/README.md
-
curl -L -o README.md https://huggingface.co/spaces/robtacconelli/Nacrith-GPU/resolve/main/README.md
902 Bytes
| title: Nacrith GPU - Neural Lossless Compression via Ensemble Context Modeling and High-Precision CDF Coding | |
| emoji: 🗜️ | |
| colorFrom: red | |
| colorTo: gray | |
| sdk: gradio | |
| sdk_version: 5.12.0 | |
| app_file: app.py | |
| pinned: true | |
| license: apache-2.0 | |
| hardware: zero-a10g | |
| short_description: Lossless compression with LLM + Arithmetic Coding | |
| # Nacrith GPU | |
| Advanced lossless compression using a neural language model (SmolLM2-135M) + arithmetic coding. | |
| Supports both **text** (NC01) and **binary** (NC02) compression. | |
| - **Text:** ~15% compression ratio -- 2.5x better than gzip | |
| - **Binary:** Hybrid format -- text regions neural-compressed, binary regions gzip/lzma-compressed | |
| - **Website:** [nacrith.com](https://nacrith.com) | |
| - **GitHub:** [github.com/st4ck/Nacrith-GPU](https://github.com/st4ck/Nacrith-GPU) | |
| - **arXiv:** [arxiv.org/abs/2602.19626](https://arxiv.org/abs/2602.19626) |