sshh12/multi_token

Embed arbitrary modalities (images, audio, documents, etc) into large language models.

38
/ 100
Emerging

This project helps you feed diverse types of information, like documents, images, audio, or video, into a large language model. You provide these various data inputs alongside your questions, and the model then processes them to give you comprehensive answers or summaries. It's designed for anyone who needs to ask complex questions that require understanding information from multiple formats, beyond just plain text.

191 stars. No commits in the last 6 months.

Use this if you need a language model to analyze or respond to prompts that include images, sounds, documents, or videos, not just text.

Not ideal if you only work with text-based data or require highly specialized, high-fidelity analysis for a single modality like only speech recognition or document summarization.

multimodal-analysis content-understanding information-extraction multimedia-processing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

191

Forks

16

Language

Python

License

Apache-2.0

Last pushed

Mar 27, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/sshh12/multi_token"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.