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

Libraries

How to use Maiasa/Maiasa with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Maiasa/Maiasa",
	filename="Maiasa_v1.0.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 Maiasa/Maiasa with llama.cpp:

Install from brew

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

Install from WinGet (Windows)

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

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

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

Use Docker

docker model run hf.co/Maiasa/Maiasa

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

Unsloth Studio new

How to use Maiasa/Maiasa 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 Maiasa/Maiasa 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 Maiasa/Maiasa to start chatting

Using HuggingFace Spaces for Unsloth

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

Docker Model Runner
How to use Maiasa/Maiasa with Docker Model Runner:
```
docker model run hf.co/Maiasa/Maiasa
```

Lemonade

How to use Maiasa/Maiasa with Lemonade:

Pull the model

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

Run and chat with the model

lemonade run user.Maiasa-{{QUANT_TAG}}

List all available models

lemonade list

My new favorite AI.

☀️ maiasa.ai

Maiasa is a next-gen, open-source language model parody that's lightning-fast, robust, safe, ethical and sustainable. You can try it for free right now!

Benefits

☀️ Fast: Often generates up to 1,000 tokens per second.
☀️ Robust: Under the hood, it's always easy to understand why the model said what it said.
☀️ Efficient: Runs even on low-end machines, and takes very little disk space.
☀️ Versatile: Performs equally on all kinds of different use cases.
☀️ Unopinionated: Responds to all prompts without going on about guidelines.
☀️ Secure: Attempts at prompt injection will have no effect on the output.
☀️ Ethical: No copyrighted data was used to train the model.
☀️ Eco-friendly: Lower resource consumption than most current LLMs.
☀️ Free: Maiasa is free to use and open-source.
☀️ Ready to use: Use it in an app like LM Studio, or try it on maiasa.ai!

Limitations

☀️ Maiasa's active vocabulary is limited to the single token "a", and it will reply to all prompts with only "a".

Downloads last month: 8

GGUF

Model size

10.9k 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