Skip to main content

Run AI models in Python. Register at https://muna.ai.

Project description

Muna for Python

Muna logo

Compile and run AI models locally & in the cloud.

Installing Muna

Muna is distributed on PyPi. This distribution contains both the Python client and the command line interface (CLI). Run the following command in terminal:

# Install Muna
$ pip install --upgrade muna

[!NOTE] Muna requires Python 3.11+

Running a Model

First, create a Muna client, specifying your access key (create one here):

from muna import Muna

# 💥 Create an OpenAI client
openai = Muna("<ACCESS KEY>").beta.openai

Next, run a model:

# 🔥 Create a chat completion
completion = openai.chat.completions.create(
  model="@openai/gpt-oss-20b",
  messages=[
    { "role": "user", "content": "What is the capital of France?" }
  ],
  acceleration="local_gpu"
)

Finally, use the results:

# 🚀 Use the results
print(completion.choices[0].message)

Useful Links

Muna is a product of NatML Inc.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

muna-0.1.7.tar.gz (30.8 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

muna-0.1.7-py3-none-any.whl (30.9 MB view details)

Uploaded Python 3

File details

Details for the file muna-0.1.7.tar.gz.

File metadata

  • Download URL: muna-0.1.7.tar.gz
  • Upload date:
  • Size: 30.8 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.15

File hashes

Hashes for muna-0.1.7.tar.gz
Algorithm Hash digest
SHA256 ad59bef2f72e430f4fcdd665b1052fa0c52c29f6fb112d7f56a00d275c636e3f
MD5 2da0dd5150a77004a080203cb5c82c3d
BLAKE2b-256 dac9633cc9958c9cb8dec5753ecc8046c1cd9eada5c4a862a641bee0924ae617

See more details on using hashes here.

File details

Details for the file muna-0.1.7-py3-none-any.whl.

File metadata

  • Download URL: muna-0.1.7-py3-none-any.whl
  • Upload date:
  • Size: 30.9 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.15

File hashes

Hashes for muna-0.1.7-py3-none-any.whl
Algorithm Hash digest
SHA256 1c3c7e37110a89410c1a2bfc49871a7dbfc6d916dba8f7b3f91c2918ac7c2858
MD5 b1d54b1f09b6cdca1844c971d0db3913
BLAKE2b-256 e5a344bf50f793ae631bf222c93a03d2ca90caf8cde02902aa1a19e4fcc4db3e

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page