Skip to main content

High-level APIs and training utilities for the LISA Vision+Audio model

Project description

lisaai

High-level, repo-independent tools for the LISA Vision+Audio model.

Install

From this folder:

pip install -e .

CLI

  • Inspect a checkpoint (folder or .safetensors):
lisa.inspect "PATH/TO/MODEL_DIR"
  • Compare param counts by saved prefixes:
lisa.compare-params "PATH/TO/MODEL_DIR"

Python API

from lisaai import inspect_checkpoint, compare_param_counts

rep = inspect_checkpoint("PATH/TO/MODEL_DIR")
print(rep["inferred_dimensions"])  # {vision_embed_dim, fusion_hidden_dim}

To use runtime loading (optional, if the original repo is available):

from lisaai import load_model
m = load_model()  # will use LISA_MODEL_PATH if set

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

lisaai-0.1.0.tar.gz (28.3 kB view details)

Uploaded Source

Built Distribution

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

lisaai-0.1.0-py3-none-any.whl (32.1 kB view details)

Uploaded Python 3

File details

Details for the file lisaai-0.1.0.tar.gz.

File metadata

  • Download URL: lisaai-0.1.0.tar.gz
  • Upload date:
  • Size: 28.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.9

File hashes

Hashes for lisaai-0.1.0.tar.gz
Algorithm Hash digest
SHA256 0178cf059a4e607b9c2a7dd38ef29cab3f41119082f3189cebb200f0064a25ba
MD5 76154b82ff9574e6c55c76fd52a50c50
BLAKE2b-256 ac51821d45f34138203ca78eedecd9b67b69b39ed2bdb86d040680c6ed138c09

See more details on using hashes here.

File details

Details for the file lisaai-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: lisaai-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 32.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.9

File hashes

Hashes for lisaai-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 08251038c62282f50865ad18e3fffcf81dfe812b7474749eb9c89b87119215c4
MD5 21ea16cef1d87ef00d1bd025577ddfe4
BLAKE2b-256 b0c920b82ed5a2f34bc031771ff0277ec61b82b91230549aef28bd83444584ca

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