|
Download README.md from KvcHub/README: direct link, hf CLI and curl.
- Browser
- Download file 2.36 kB
-
https://huggingface.co/spaces/KvcHub/README/resolve/main/README.md
- Command line
-
hf download hf://spaces/KvcHub/README/README.md
-
curl -L -o README.md https://huggingface.co/spaces/KvcHub/README/resolve/main/README.md
2.36 kB
| title: KvcHub Labs | |
| emoji: π‘οΈ | |
| colorFrom: blue | |
| colorTo: indigo | |
| pinned: false | |
| <div align="center"> | |
| # KvcHub Labs | |
| **On-Device Privacy & High-Speed Neural Intelligence.** | |
| [π Website](https://kvchub.com) β’ [π€ Hugging Face](https://huggingface.co/KvcHub) β’ [π¦ PyPI (`kava-privacy`)](https://pypi.org) | |
| </div> | |
| --- | |
| ## π About | |
| **KvcHub Labs** researches and builds ultra-lightweight, hardware-accelerated, zero-trust AI models. Our mission is to make advanced privacy redaction and neural intelligence run **100% locally on-device** with zero cloud data leakage and sub-millisecond execution speeds. | |
| ## π Core Focus Areas | |
| * π **Zero Data Leakage (100% On-Device):** Text never leaves local memory, supporting HIPAA, GDPR, and SOC2 compliance. | |
| * β‘ **Sub-Millisecond Speed:** Optimized for ultra-fast local inference without cloud network roundtrips. | |
| * π§ͺ **High-Precision Redaction:** Engineered to avoid false positives on scientific constants, subnet masks, legal citations, and financial tickers. | |
| * π **Zero-Shot Multilingual Detection:** Recognizes international names, addresses, and phone numbers out of the box. | |
| * π **Real-Time Streaming:** Sanitizes live streaming LLM outputs token-by-token on the fly. | |
| ## π€ Models | |
| | Model | Task | Parameters | Notes | | |
| | :--- | :--- | :--- | :--- | | |
| | [`KvcHub/KaiLu-3-Pro`](https://huggingface.co/KvcHub/KaiLu-3-Pro) | Text Generation | `1.0B` | Newest KaiLu chat model, trained from scratch. One GGUF (Q8_0) for llama.cpp, Ollama and LM Studio, plus safetensors. Apache-2.0. | | |
| | [`KvcHub/KaiLu3`](https://huggingface.co/KvcHub/KaiLu3) | Text Generation | `0.3B` | KaiLu 3 base model (329M), trained from scratch. | | |
| | [`KvcHub/KaiLu-2-2B-GGUF`](https://huggingface.co/KvcHub/KaiLu-2-2B-GGUF) | Text Generation | `2B` | Quantized `GGUF` build for fast local inference. | | |
| | [`KvcHub/KaiLu-2-933M`](https://huggingface.co/KvcHub/KaiLu-2-933M) | Text Generation | `1.0B` (`933M`) | Compact generative language model. | | |
| | [`KvcHub/Kava-Privacy-2.01M-mlx`](https://huggingface.co/KvcHub/Kava-Privacy-2.01M-mlx) | Token Classification | `2.01M` | MLX-optimized on-device PII redaction model. | | |
| | [`KvcHub/Kava-Privacy-636k-mlx`](https://huggingface.co/KvcHub/Kava-Privacy-636k-mlx) | Token Classification | `636k` | Ultra-compact MLX model for sub-millisecond PII detection. | | |