Introduction
MAV - Model Activity Visualiser (for LLMs)
Getting started
METHOD 1: If uv is installed:
uv run --with openmav mav
or
uv run --with git+https://github.com/attentionmech/mav mav --model gpt2 --prompt "hello mello"
METHOD 2: Without uv:
-
Set up and activate a virtual environment
-
Install the package:
pip install openmav
or
pip install git+https://github.com/attentionmech/mav
-
Run:
mav --model gpt2 --prompt "hello mello"
-
or Import
from openmav.mav import MAV MAV("gpt2", "Hello")
METHOD 3: Locally from scratch
- git clone https://github.com/attentionmech/mav
- cd mav
- Set up and activate a virtual environment
- Install the package:
pip install .
- Run:
mav --model gpt2 --prompt "hello mello"
METHOD 4: Inside Jupyter notebook/Colab
You can replace gpt2 with other Hugging Face models for example:
meta-llama/Llama-3.2-1BHuggingFaceTB/SmolLM-135Mgpt2-mediumgpt2-large
Tutorials
Writing your custom plugin tutorial in colab
running MAV with a training loop with a custom model (not pretrained one)
uv run examples/test_vis_train_loop.py
running MAV with custom panel selection and arrangement
uv run --with git+https://github.com/attentionmech/mav mav --model gpt2 --num-grid-rows 3 --selected-panels generated_text attention_entropy top_predictions --max-bar-length 20 --refresh-rate 0 --max-new-tokens 10000
Demos
- Basic plugins
- Entropy Fire plugin
- interactive mode
- limit chars
- sample with temperature
- running with custom model
- panel selection
- running in colab notebook
Note: explore it using the command line help as well, since many sampling params are exposed.
Contributing
Clone the repository and install the package in development mode:
git clone https://github.com/attentionmech/mav
cd mav
# recommended
uv sync
# if you don't use uv
pip install -e .
Metadata
Release files for openmav 0.0.12
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| openmav-0.0.12.tar.gz | 14.7 kB | Without provenance | Details for openmav-0.0.12.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| openmav-0.0.12-py3-none-any.whl | Python 3 | none | any | Details for openmav-0.0.12-py3-none-any.whl |
Total release size: 32.6 kB
Release files / openmav-0.0.12.tar.gz
| Download URL | openmav-0.0.12.tar.gz |
|---|---|
| Size | 14.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
c4726b00f453bcf40714f9db375d19f6d17f4bd79fcb83b1040aa790881c83d5
|
|
BLAKE2b-256 checksum How to use checksums |
cfc5177d2157090b5f8d12cb7562d65c46a44287a6ae0ac4bf745580f997ab59
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.12.7
|
Release files / openmav-0.0.12-py3-none-any.whl
| Download URL | openmav-0.0.12-py3-none-any.whl |
|---|---|
| Size | 17.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
0a8e4876a9ca76f5b550737b85dca93f291280c9d21e781146099874c0dc19cc
|
|
BLAKE2b-256 checksum How to use checksums |
80f404ec800d997da14aeb9e838c30c0035ddbfb5b3eb393d8a9eb14f360a7ec
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.12.7
|
Security for openmav 0.0.12
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.