Instructions to use AGofficial/AgGPT-9 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AGofficial/AgGPT-9 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AGofficial/AgGPT-9",
	filename="AgGPT-9.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

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 Studio

How to use AGofficial/AgGPT-9 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for AGofficial/AgGPT-9 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for AGofficial/AgGPT-9 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AGofficial/AgGPT-9 to start chatting

Atomic Chat new
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

AgGPT-9 and AgGPT-6m - Local AI Models

Overview

This repository contains two versions of the AgGPT model:

AgGPT-9: The full version of the AgGPT model, offering advanced AI capabilities for high-performance systems.
AgGPT-6m: A lighter version of AgGPT, optimized for devices with less computing power.

Both models are designed for local use and provide advanced AI assistance.

Features

AgGPT-9:
- High-performance model optimized for more capable systems.
- Suitable for intensive computational tasks.
- Can process larger context windows and generate high-quality responses.
AgGPT-6m:
- A lighter, more efficient version for less computing-capable devices.
- Optimized for devices with lower memory and processing power.
- Provides similar functionality to AgGPT-9, but with reduced resource demands.

Requirements

Before running the models, make sure your system meets the following requirements:

Python 3.11.7 or higher
llama_cpp library installed (use pip install llama_cpp)
A compatible device for running the models (refer to individual model requirements below)

AgGPT-9 Requirements:

High-performance machine
8GB+ RAM
NPU recommended

AgGPT-6m Requirements:

1GB+ RAM
Sufficient storage

License

The software is released under the AGGPT-9 Software License Agreement. For full details, please refer to the LICENSE file.

Downloads last month: 1

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support