Instructions to use AGofficial/AgGPT-10 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AGofficial/AgGPT-10 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AGofficial/AgGPT-10",
	filename="aggpt10.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-10 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AGofficial/AgGPT-10
# Run inference directly in the terminal:
llama-cli -hf AGofficial/AgGPT-10

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AGofficial/AgGPT-10
# Run inference directly in the terminal:
llama-cli -hf AGofficial/AgGPT-10

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-10
# Run inference directly in the terminal:
./llama-cli -hf AGofficial/AgGPT-10

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-10
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AGofficial/AgGPT-10

Use Docker

docker model run hf.co/AGofficial/AgGPT-10

LM Studio
Jan
Ollama
How to use AGofficial/AgGPT-10 with Ollama:
```
ollama run hf.co/AGofficial/AgGPT-10
```

Unsloth Studio

How to use AGofficial/AgGPT-10 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-10 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-10 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-10 to start chatting

How to use AGofficial/AgGPT-10 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf AGofficial/AgGPT-10

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "AGofficial/AgGPT-10"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use AGofficial/AgGPT-10 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf AGofficial/AgGPT-10

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default AGofficial/AgGPT-10

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use AGofficial/AgGPT-10 with Docker Model Runner:
```
docker model run hf.co/AGofficial/AgGPT-10
```

Lemonade

How to use AGofficial/AgGPT-10 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AGofficial/AgGPT-10

Run and chat with the model

lemonade run user.AgGPT-10-{{QUANT_TAG}}

List all available models

lemonade list

AgGPT-10

AgGPT-10 is a milestone in our AI research, representing a significant leap in the capabilities of generative AI. It is designed to assist users in various tasks, from content generation to complex problem-solving.

AgGPT-10 is almost 3 times smaller in size than AgGPT-9, yet it is many times more powerful. This is achieved through advanced model architecture and training techniques, making it a highly efficient and effective tool for a wide range of applications.

Developers can use aggpt10.py to interact with the AgGPT-10 model.

from aggpt10 import AgGPT

AI = AgGPT("aggpt10.gguf")

print(AI.ask("hello"))

# Output: "Hello! How can I assist you today?"

with this simple aproach, you can easily integrate AgGPT-10 into your applications and leverage its capabilities for various tasks.

We are excited to see how the community will use AgGPT-10 and look forward to your feedback. Please feel free to reach out with any questions or suggestions.

This repository is licensed under the MIT License. See the LICENSE file for more information.

Downloads last month: 1

GGUF

Model size

3B params

Architecture

qwen2

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