Skip to main content

Minimal CLI tool to summarize any text locally with help of LLM!

Project description

Sumsum

A minimal CLI tool to locally summarize any text using LLM!

Built around Ollama and fine-tuned version of Llama3.2-3B-Instruct

Installation:

pip install sum-sum

Setup:

  • Run the init command to check dependency, download model and generate modelfile:
    sumsum init
    

Usage

  • Use the command run with your text file path:
    sumsum run path\to\file.txt
    
  • you can also use the flag --verbose to get additional information: (time taken to load the model, time taken for generating new tokens,number of generated tokens etc)
    sumsum run path\to\file.txt --verbose
    

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

sum_sum-0.1.0.1.tar.gz (17.9 kB view details)

Uploaded Source

Built Distribution

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

sum_sum-0.1.0.1-py3-none-any.whl (4.5 kB view details)

Uploaded Python 3

File details

Details for the file sum_sum-0.1.0.1.tar.gz.

File metadata

  • Download URL: sum_sum-0.1.0.1.tar.gz
  • Upload date:
  • Size: 17.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.4.29

File hashes

Hashes for sum_sum-0.1.0.1.tar.gz
Algorithm Hash digest
SHA256 3d5781d6b5a1763e5d65b5f064f59c26da69dd5d725d33b48f52f11305883bbb
MD5 77d99f7bc1ae6fe1aa5bee36282368b6
BLAKE2b-256 c9e534b5c8d95ee6988d613935baa03d0ca977b1a0a17c261100bdd49cd1a397

See more details on using hashes here.

File details

Details for the file sum_sum-0.1.0.1-py3-none-any.whl.

File metadata

  • Download URL: sum_sum-0.1.0.1-py3-none-any.whl
  • Upload date:
  • Size: 4.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.4.29

File hashes

Hashes for sum_sum-0.1.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 1ee5222d7bf8b68a8b19fc0217f61559d938ca3348cfb74c904eaab4913a2c41
MD5 ec59be6b3d000518448e9afcd3219be7
BLAKE2b-256 595c672740a9bea4c057fe2f4acaa98f354f706bef33eac4d41bdd0e957a19c3

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