Instructions to use AGofficial/AGR1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AGofficial/AGR1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AGofficial/AGR1",
	filename="AGR1.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/AGR1 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/AGR1
# Run inference directly in the terminal:
llama cli -hf AGofficial/AGR1

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AGofficial/AGR1
# Run inference directly in the terminal:
llama cli -hf AGofficial/AGR1

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/AGR1
# Run inference directly in the terminal:
./llama-cli -hf AGofficial/AGR1

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/AGR1
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AGofficial/AGR1

Use Docker

docker model run hf.co/AGofficial/AGR1

LM Studio
Jan
Ollama
How to use AGofficial/AGR1 with Ollama:
```
ollama run hf.co/AGofficial/AGR1
```

Unsloth Studio

How to use AGofficial/AGR1 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/AGR1 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/AGR1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AGofficial/AGR1 to start chatting

Atomic Chat new
Docker Model Runner
How to use AGofficial/AGR1 with Docker Model Runner:
```
docker model run hf.co/AGofficial/AGR1
```

Lemonade

How to use AGofficial/AGR1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AGofficial/AGR1

Run and chat with the model

lemonade run user.AGR1-{{QUANT_TAG}}

List all available models

lemonade list

AGR1

Overview

AGR1 is a state of the art Cot (chain of thought) model that is able to think and reason before responding. It is based on the AgGPT-9 architecture. The model is able to generate human-like responses to a wide range of prompts and is able to generate text that is coherent and contextually relevant.

Requirements

Before running the model, 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 model

AGR1 Requirements:

High-performance machine
8GB+ RAM
NPU recommended

License

The software is released under the MIT license. For more details, refer to the LICENSE file.

Downloads last month: 2

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

Model tree for AGofficial/AGR1

Quantizations

1 model