Download README.md from KvcHub/README: direct link, hf CLI and curl.
- Browser
- Download file 4.56 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
title: KvcHub Labs
emoji: π‘οΈ
colorFrom: blue
colorTo: indigo
pinned: false
KvcHub Labs
On-Device Privacy & High-Speed Neural Intelligence.
π Website β’ π€ Hugging Face β’ π¦ PyPI (kava-privacy) β’ Ki Complete for VS Code β’ Ki Complete on Open VSX
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/Ki-Complete-1.5B |
Code Completion | 1.5B |
The default model of Ki Complete, KvcHub's code autocomplete for VS Code and Antigravity. Fine-tuned from Qwen2.5-Coder-1.5B; GGUF (Q8_0, plus a 4-bit Q4_K_M "Small" for 8 GB computers) and the LoRA. Apache-2.0. |
KvcHub/Ki-Complete-7B |
Code Completion | 7B |
Ki Complete's larger model: the most accurate on real code, about 4 times slower; for 16 GB+ computers. Fine-tuned from Qwen2.5-Coder-7B; one GGUF (Q8_0) plus the LoRA. Apache-2.0. |
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 |
Text Generation | 0.3B |
KaiLu 3 base model (329M), trained from scratch. |
KvcHub/KaiLu-2-2B-GGUF |
Text Generation | 2B |
Quantized GGUF build for fast local inference. |
KvcHub/KaiLu-2-933M |
Text Generation | 1.0B (933M) |
Compact generative language model. |
KvcHub/Kava-Privacy-2.01M-mlx |
Token Classification | 2.01M |
MLX-optimized on-device PII redaction model. |
KvcHub/Kava-Privacy-636k-mlx |
Token Classification | 636k |
Ultra-compact MLX model for sub-millisecond PII detection. |
Ki Complete
Ki Complete is KvcHub's code autocomplete extension for VS Code and Antigravity: code suggestions as you type, shown in green, from a model that runs on your own computer. Your code never leaves your machine, it works offline, and it's free. It turns off GitHub Copilot's (in VS Code) or Antigravity's own suggestions once, so the two don't compete, with a button to turn them back on.
Install it:
- VS Code: Ki Complete on the Visual Studio Marketplace
- Antigravity, VSCodium, Cursor and other editors that use Open VSX:
kvchub.ki-completeon Open VSX, published by KvcHub under thekvchubnamespace - Direct download: the .vsix from kvchub.com
Models, chosen from the Ki status bar menu and downloaded once:
KvcHub/Ki-Complete-1.5B(default): quickest, about 0.23 seconds per suggestion on an Apple M5 Pro; also as Ki Complete Small (4-bit, 990 MB)KvcHub/Ki-Complete-7B: most accurate on real code (49.7% / 37.7% of line endings exactly right, against 43.1% / 35.7%), about 1 second per suggestion
More at kvchub.com.