Skip to main content

Easy one‑liner training + inference tool for the uniform LoRA VLM.

Project description

uniform‑vlm

A lightweight wrapper Python package for training and inference with NuExtract‑style LoRA adapters.

pip install uniform-vlm

Inference

# CLI
uniform-vlm infer images/ --csv preds.csv

# Python
from uniform_vlm.infer import images_to_csv
images_to_csv("images", "preds.csv")

Training (continue fine‑tuning existing adapter by default)

uniform-vlm train data/train.csv --image-col path --label-col label_json \
             --output-dir output/my_adapter

See the Colab walkthrough ➜ https://colab.research.google.com/drive/1ndRcS9EMcunvrLorQdP97InvCvkEETjJ?usp=sharing


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

uniform_vlm-0.1.2.tar.gz (6.9 kB view details)

Uploaded Source

Built Distribution

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

uniform_vlm-0.1.2-py3-none-any.whl (9.0 kB view details)

Uploaded Python 3

File details

Details for the file uniform_vlm-0.1.2.tar.gz.

File metadata

  • Download URL: uniform_vlm-0.1.2.tar.gz
  • Upload date:
  • Size: 6.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.9.21

File hashes

Hashes for uniform_vlm-0.1.2.tar.gz
Algorithm Hash digest
SHA256 9e3d1379a92ce20ea16107a0ac607a7bfe8b0a83d42fb53d396ebccb3664a016
MD5 58dcfdec61a81b670316e3824814b946
BLAKE2b-256 f9aa12218c8fd921a23fc1c8b36c28320e38406f63ab34eab73bac9ae92ebffe

See more details on using hashes here.

File details

Details for the file uniform_vlm-0.1.2-py3-none-any.whl.

File metadata

  • Download URL: uniform_vlm-0.1.2-py3-none-any.whl
  • Upload date:
  • Size: 9.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.9.21

File hashes

Hashes for uniform_vlm-0.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 ad6925a64787423d91a5de4ba1b2424aea36b04965fdb17eec15f1d9df11025c
MD5 8c67f9109a31b53723e2c2b60919f279
BLAKE2b-256 28030943106bd9d5481ec4e80e726c5ec3ccd35fe658b38764b5ddfc6d26d22f

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