zygai / README.md
ZygAI's picture
Update README.md
fcf909b verified
metadata
license: apache-2.0
language:
  - en
  - lt
pipeline_tag: text-generation
tags:
  - gguf
  - llama.cpp
  - openwebui
  - lithuanian
  - bilingual
  - local-ai

🧠 ZygAI β€” Neutral Bilingual AI Engine (LT / EN)

ZygAI is a neutral, locally hosted AI engine designed for Lithuanian πŸ‡±πŸ‡Ή and English πŸ‡¬πŸ‡§ language tasks.
It is built for local inference, server-based usage, and runtime personas.

ZygAI is a base engine, not a chatbot persona.
Behavior and specialization are applied at runtime (OpenWebUI / API).

✨ Key Features

  • πŸ‡±πŸ‡Ή / πŸ‡¬πŸ‡§ True bilingual support
  • ⚑ Optimized GGUF models for llama.cpp
  • 🧩 Supports runtime personas (MiniGPTs, system prompts)
  • 🧠 Clean identity β€” no vendor branding
  • πŸ–₯️ Designed for systemd + server deployments
  • πŸ”€ Supports GGUF shards (no merge required)

🧠 Architecture Overview

ZygAI (base engine)
β”œβ”€β”€ Q4 β†’ fast / high throughput
β”œβ”€β”€ Q5 β†’ balanced / general usage
└── Q8 β†’ high quality / reasoning

  • ZygAI = neutral engine
  • No hardcoded system prompt in the model

πŸ“¦ Available Quantizations

Quantization Purpose Notes
Q4_K_M Fast Best speed, low memory
Q5_K_M Balanced Default general use
Q8_0 High quality Best reasoning, higher RAM

Models may be provided as GGUF shards (-00001-of-00002.gguf).
llama.cpp loads shards automatically β€” no merge required.

πŸš€ Running ZygAI (llama.cpp server)

Example: Q4 (shard-based)

./llama-server \
  -m ZygAI-q4_k_m-00001-of-00002.gguf \
  --host 0.0.0.0 \
  --port 8081 \
  --ctx-size 4096 \
  --threads 4 \
  --batch-size 2048 \
  --jinja

Multiple models (recommended)

Model Port
Q4 8081
Q5 8082
Q8 8083

🧰 Using with OpenWebUI

  • Provider: OpenAI (local)

  • Base URL: http://127.0.0.1:PORT/v1

  • Auth: none

Important

ZygAI is designed for llama.cpp backend.
System prompts and personas work correctly only with llama.cpp, not Ollama.

🎭 Personas (Recommended)

ZygAI is intentionally neutral.
Specialization is applied via runtime personas:

🌍 Language Behavior

  • Responds in the same language as the user

  • No automatic language switching

  • No mixed-language replies unless requested

Examples:
User (EN):
> What is Lithuania?
Assistant:
> Lithuania is a country located in the Baltic region of Eastern Europe.
User (LT):
> Kada Lietuva Δ―stojo Δ― Europos SΔ…jungΔ…?.
Assistant:
> Lietuva Δ―stojo Δ― Europos SΔ…jungΔ… 2004 m. geguΕΎΔ—s 1 d.

πŸ“œ License

Apache 2.0
This repository provides inference-only model files.
Base model weights originate from publicly available sources and are redistributed according to their respective licenses.

πŸ”’ Notes

  • ZygAI is not ChatGPT

  • ZygAI is not a vendor-branded assistant

  • ZygAI is designed for local-first, privacy-respecting AI

πŸ“– Citation

If you use ZygAI in research, development, or documentation, please cite it as follows:

@software{zygai-7b,
  title        = {ZygAI: Neutral Bilingual AI Engine for Lithuanian and English},
  author       = {MaΕΎeika, Ε½ygimantas},
  year         = {2025},
  publisher    = {Hugging Face},
  url          = {https://huggingface.co/ZygAI},
  license      = {Apache-2.0},
  note         = {Local-first GGUF models optimized for llama.cpp with runtime personas}
}