Instructions to use AGofficial/AgGPT-9 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 AGofficial/AgGPT-9 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 AGofficial/AgGPT-9 # Run inference directly in the terminal: llama cli -hf AGofficial/AgGPT-9
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf AGofficial/AgGPT-9 # Run inference directly in the terminal: llama cli -hf AGofficial/AgGPT-9
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 AGofficial/AgGPT-9 # Run inference directly in the terminal: ./llama-cli -hf AGofficial/AgGPT-9
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 AGofficial/AgGPT-9 # Run inference directly in the terminal: ./build/bin/llama-cli -hf AGofficial/AgGPT-9
Use Docker
docker model run hf.co/AGofficial/AgGPT-9
- LM Studio
- Jan
- Ollama
How to use AGofficial/AgGPT-9 with Ollama:
ollama run hf.co/AGofficial/AgGPT-9
- Unsloth Desktop
- Docker Model Runner
How to use AGofficial/AgGPT-9 with Docker Model Runner:
docker model run hf.co/AGofficial/AgGPT-9
- Lemonade
How to use AGofficial/AgGPT-9 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull AGofficial/AgGPT-9
Run and chat with the model
lemonade run user.AgGPT-9-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
Download AgGPT-9.py from AGofficial/AgGPT-9: direct link, hf CLI and curl.
- Browser
- Download file 833 Bytes
-
https://huggingface.co/AGofficial/AgGPT-9/resolve/main/AgGPT-9.py
- Command line
-
hf download hf://AGofficial/AgGPT-9/AgGPT-9.py
-
curl -L -o AgGPT-9.py https://huggingface.co/AGofficial/AgGPT-9/resolve/main/AgGPT-9.py
833 Bytes
| from llama_cpp import Llama | |
| def run_local_llm(): | |
| print("Loading AgGPT-9... (This may take a moment)") | |
| model_path = "./AgGPT-9.gguf" | |
| model = Llama(model_path=model_path, n_ctx=2048, n_gpu_layers=35) | |
| print("Model loaded. Type 'exit' to quit.") | |
| while True: | |
| prompt = input("\nEnter your prompt: ") | |
| if prompt.lower() == 'exit': | |
| break | |
| messages = [ | |
| {"role": "system", "content": "You are AgGPT-9, an advanced AI assistant created by AG, the 9th series of the AgGPT models."}, | |
| {"role": "user", "content": prompt} | |
| ] | |
| output = model.create_chat_completion(messages, max_tokens=550, temperature=0.7) | |
| print("\nGenerated text:") | |
| print(output["choices"][0]["message"]["content"]) | |
| if __name__ == "__main__": | |
| run_local_llm() | |