Instructions to use ReallyFloppyPenguin/Arch-Agent-7B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ReallyFloppyPenguin/Arch-Agent-7B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ReallyFloppyPenguin/Arch-Agent-7B-GGUF",
	filename="model-f16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use ReallyFloppyPenguin/Arch-Agent-7B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ReallyFloppyPenguin/Arch-Agent-7B-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf ReallyFloppyPenguin/Arch-Agent-7B-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ReallyFloppyPenguin/Arch-Agent-7B-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf ReallyFloppyPenguin/Arch-Agent-7B-GGUF:F16

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 ReallyFloppyPenguin/Arch-Agent-7B-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf ReallyFloppyPenguin/Arch-Agent-7B-GGUF:F16

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 ReallyFloppyPenguin/Arch-Agent-7B-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ReallyFloppyPenguin/Arch-Agent-7B-GGUF:F16

Use Docker

docker model run hf.co/ReallyFloppyPenguin/Arch-Agent-7B-GGUF:F16

LM Studio
Jan
Ollama
How to use ReallyFloppyPenguin/Arch-Agent-7B-GGUF with Ollama:
```
ollama run hf.co/ReallyFloppyPenguin/Arch-Agent-7B-GGUF:F16
```

Unsloth Studio new

How to use ReallyFloppyPenguin/Arch-Agent-7B-GGUF 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 ReallyFloppyPenguin/Arch-Agent-7B-GGUF 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 ReallyFloppyPenguin/Arch-Agent-7B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ReallyFloppyPenguin/Arch-Agent-7B-GGUF to start chatting

Docker Model Runner
How to use ReallyFloppyPenguin/Arch-Agent-7B-GGUF with Docker Model Runner:
```
docker model run hf.co/ReallyFloppyPenguin/Arch-Agent-7B-GGUF:F16
```

Lemonade

How to use ReallyFloppyPenguin/Arch-Agent-7B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ReallyFloppyPenguin/Arch-Agent-7B-GGUF:F16

Run and chat with the model

lemonade run user.Arch-Agent-7B-GGUF-F16

List all available models

lemonade list

katanemo/Arch-Agent-7B - GGUF

This repository contains GGUF quantizations of katanemo/Arch-Agent-7B.

About GGUF

GGUF is a quantization method that allows you to run large language models on consumer hardware by reducing the precision of the model weights.

Files

Filename	Quant type	File Size	Description
model-f16.gguf	f16	Large	Original precision
model-q4_0.gguf	Q4_0	Small	4-bit quantization
model-q4_1.gguf	Q4_1	Small	4-bit quantization (higher quality)
model-q5_0.gguf	Q5_0	Medium	5-bit quantization
model-q5_1.gguf	Q5_1	Medium	5-bit quantization (higher quality)
model-q8_0.gguf	Q8_0	Large	8-bit quantization

Usage

You can use these models with llama.cpp or any other GGUF-compatible inference engine.

llama.cpp

./llama-cli -m model-q4_0.gguf -p "Your prompt here"

Python (using llama-cpp-python)

from llama_cpp import Llama

llm = Llama(model_path="model-q4_0.gguf")
output = llm("Your prompt here", max_tokens=512)
print(output['choices'][0]['text'])

Original Model

This is a quantized version of katanemo/Arch-Agent-7B. Please refer to the original model card for more information about the model's capabilities, training data, and usage guidelines.