Skip to main content

LocalCat

PyPI version Documentation Status Python Versions GitHub

LocalCat is designed to make the LLM strategy easy to implement. It provides a simple API and an intuitive interface for loading, fine-tuning, and deploying large deep learning models. With LocalCat, you can easily fine-tune pre-trained models on your own data and leverage their power for your specific tasks.

Tasks

Translation

LocalCat offers user-friendly tools for translation tasks, allowing the translator to be deployed as an endpoint or for batch processing of pandas dataframes. Additionally, it provides fine-tuning capabilities for cloud deployment.

  1. Load pre-trained LLMs locally or from HuggingFace
  2. Fine-tune the LLMs
  3. Deployment as an endpoint on AWS

Chat

(On the way. Stay tuned.)

Install

pip install localcat

The Story behind LocalCat

LocalCat is named after a cat named Hulu (葫芦), owned by my friend Flora. The inspiration for the name came from the cat's playful and curious nature, which aligns with the goals of the LocalCat package.

Metadata

Release files for localcat 0.0.10

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distribution (wheel)

Table of built distributions (wheels) for localcat 0.0.10
File Interpreter ABI Platform Actions
localcat-0.0.10-py3-none-any.whl Python 3 none any Details for localcat-0.0.10-py3-none-any.whl

Release files / localcat-0.0.10-py3-none-any.whl

Download URL localcat-0.0.10-py3-none-any.whl
Size 13.1 kB
Tags Python 3
SHA-256 checksum
How to use checksums
c7d016638e326d33a4b7d52672af7febfee10802e9e962a69caafede5cd339d0
BLAKE2b-256 checksum
How to use checksums
d1e9704989389c34fe9c7e5c64867c51cc266cf3b2958e30cc7a2c860c09ac17
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.9.13

Security for localcat 0.0.10

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.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page