Model Activation Visualizer
Project description
+===========================================================================+
| _____ _____ _____ |
| /\ \ /\ \ /\ \ |
| /::\____\ /::\ \ /::\____\ |
| /::::| | /::::\ \ /:::/ / |
| /:::::| | /::::::\ \ /:::/ / |
| /::::::| | /:::/\:::\ \ /:::/ / |
| /:::/|::| | /:::/__\:::\ \ /:::/____/ |
| /:::/ |::| | /::::\ \:::\ \ |::| | |
| /:::/ |::|___|______ /::::::\ \:::\ \ |::| | _____ |
| /:::/ |::::::::\ \ /:::/\:::\ \:::\ \ |::| | /\ \ |
|/:::/ |:::::::::\____\/:::/ \:::\ \:::\____\ |::| | /::\____\|
|\::/ / ~~~~~/:::/ /\::/ \:::\ /:::/ / |::| | /:::/ /|
| \/____/ /:::/ / \/____/ \:::\/:::/ / |::| | /:::/ / |
| /:::/ / \::::::/ / |::|____|/:::/ / |
| /:::/ / \::::/ / |:::::::::::/ / |
| /:::/ / /:::/ / \::::::::::/____/ |
| /:::/ / /:::/ / ~~~~~~~~~~ |
| /:::/ / /:::/ / |
| /:::/ / /:::/ / |
| \::/ / \::/ / |
| \/____/ \/____/ |
+===========================================================================+
Model Activations Visualiser
Getting started
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"
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"
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"
You can replace gpt2 with other Hugging Face models for example:
meta-llama/Llama-3.2-1BHuggingFaceTB/SmolLM-135Mgpt2-mediumgpt2-large
Demos
Note: explore it using the command line help as well, since many sampling params are exposed.
Contributing
IMP NOTE: The design is not good for scaling it right now to multiple backends, and stuff which i am planning.. so your pull requests will have to wait for sometime
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file openmav-0.0.5.tar.gz.
File metadata
- Download URL: openmav-0.0.5.tar.gz
- Upload date:
- Size: 8.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
2cced952dc2094815ae99a4d37f3bb0de617c69e647911959f979ca6eb450d4b
|
|
| MD5 |
5e3334f1785630eb21f8ea8dff3ec593
|
|
| BLAKE2b-256 |
f049a7d87cd02f30ae95f07d0116fdef113823ea910bdaf6a4658a7eb15988a0
|
File details
Details for the file openmav-0.0.5-py3-none-any.whl.
File metadata
- Download URL: openmav-0.0.5-py3-none-any.whl
- Upload date:
- Size: 8.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
a17588f85c5b1c7f9d049b56bafbc62dcce38538032f184c3ad2c607713e3f4c
|
|
| MD5 |
d4d970e6f3e93e3d598e22b28d7fa7e1
|
|
| BLAKE2b-256 |
ab9b7fe507a7c6f55d705110f492d3e7b027966138440b9f402c8822871190d7
|