Text Generation
GGUF
English
Māori
llama.cpp
abteex-ai-labs
aotearoa
chat
local-first
lumynax
multilingual
new-zealand
sovereign-ai
yi
vllm
vllm-compatible
vllm-experimental
nvidia-nim
nim-compatible
nim-candidate
nvidia-nemo
nem
nvidia-nemo-pathway
nem-pathway
nem-convert-required
legacy
outdated
imatrix
conversational
Instructions to use AbteeXAILab/lumynax-chat-yi-15-34b-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use AbteeXAILab/lumynax-chat-yi-15-34b-gguf with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf AbteeXAILab/lumynax-chat-yi-15-34b-gguf:Q4_K_M # Run inference directly in the terminal: llama cli -hf AbteeXAILab/lumynax-chat-yi-15-34b-gguf:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf AbteeXAILab/lumynax-chat-yi-15-34b-gguf:Q4_K_M # Run inference directly in the terminal: llama cli -hf AbteeXAILab/lumynax-chat-yi-15-34b-gguf:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf AbteeXAILab/lumynax-chat-yi-15-34b-gguf:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf AbteeXAILab/lumynax-chat-yi-15-34b-gguf:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf AbteeXAILab/lumynax-chat-yi-15-34b-gguf:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf AbteeXAILab/lumynax-chat-yi-15-34b-gguf:Q4_K_M
Use Docker
docker model run hf.co/AbteeXAILab/lumynax-chat-yi-15-34b-gguf:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use AbteeXAILab/lumynax-chat-yi-15-34b-gguf with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AbteeXAILab/lumynax-chat-yi-15-34b-gguf" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AbteeXAILab/lumynax-chat-yi-15-34b-gguf", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/AbteeXAILab/lumynax-chat-yi-15-34b-gguf:Q4_K_M
- Ollama
How to use AbteeXAILab/lumynax-chat-yi-15-34b-gguf with Ollama:
ollama run hf.co/AbteeXAILab/lumynax-chat-yi-15-34b-gguf:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use AbteeXAILab/lumynax-chat-yi-15-34b-gguf with Docker Model Runner:
docker model run hf.co/AbteeXAILab/lumynax-chat-yi-15-34b-gguf:Q4_K_M
- Lemonade
How to use AbteeXAILab/lumynax-chat-yi-15-34b-gguf with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull AbteeXAILab/lumynax-chat-yi-15-34b-gguf:Q4_K_M
Run and chat with the model
lemonade run user.lumynax-chat-yi-15-34b-gguf-Q4_K_M
List all available models
lemonade list
- Atomic Chat
| """ | |
| Lumynax Chat Yi 15 34B Gguf — LumynaX quickstart (clone & run). | |
| This loads the GGUF that ships with this repo. No upstream HF call needed | |
| once you've done `hf download AbteeXAILab/lumynax-chat-yi-15-34b-gguf`. | |
| Usage: | |
| python quickstart.py # one-shot demo prompt | |
| python quickstart.py --interactive # REPL | |
| """ | |
| from __future__ import annotations | |
| import argparse, glob, os, sys | |
| from pathlib import Path | |
| LUMYNAX_SYSTEM = "You are LumynaX, the AbteeX AI Labs assistant from Aotearoa New Zealand. Ko te marama te tuapapa. Answer with care; cite uncertainty; refuse unsafe asks." | |
| DEMO_PROMPT = "Explain in 3 bullets why local-first AI matters for Aotearoa New Zealand." | |
| # Locate the primary GGUF that was downloaded alongside this script. | |
| HERE = Path(__file__).resolve().parent | |
| PRIMARY = HERE / r"Yi-1.5-34B-Chat-Q4_K_M.gguf" | |
| def main(): | |
| from llama_cpp import Llama | |
| p = argparse.ArgumentParser() | |
| p.add_argument("--interactive", action="store_true") | |
| p.add_argument("--prompt", default=DEMO_PROMPT) | |
| args = p.parse_args() | |
| if not PRIMARY.exists(): | |
| print(f"[lumynax] primary weight file missing: {PRIMARY}", file=sys.stderr) | |
| print(f"[lumynax] run: hf download AbteeXAILab/lumynax-chat-yi-15-34b-gguf --local-dir <dir> first.", file=sys.stderr) | |
| sys.exit(2) | |
| print(f"[lumynax] loading {PRIMARY.name}{shard_log_suffix}") | |
| llm = Llama(model_path=str(PRIMARY), n_ctx=16384, | |
| n_gpu_layers=int(os.environ.get("N_GPU_LAYERS","-1")), verbose=False) | |
| def chat(user): | |
| out = llm.create_chat_completion(messages=[ | |
| {"role":"system","content":LUMYNAX_SYSTEM}, | |
| {"role":"user","content":user}, | |
| ], max_tokens=512, temperature=0.4) | |
| return out["choices"][0]["message"]["content"] | |
| if args.interactive: | |
| print("[lumynax] interactive mode — empty line exits.") | |
| while True: | |
| try: q = input("you> ").strip() | |
| except EOFError: break | |
| if not q: break | |
| print("lumynax> " + chat(q)) | |
| else: | |
| print(chat(args.prompt)) | |
| if __name__ == "__main__": | |
| main() | |