Falcon LLMs Hackathon sponsored by GAIA Summary
Join us for an exhilarating 4-days hackathon centered around Falcon LLMs, a cutting-edge language model. The hackathon is sponsored by GAIA, the leading startup acceleration program, providing participants with the opportunity to apply for the next cohort and build innovative companies in Saudi Arabia.
Hackathon Overview
Our AI hackathon brought together a diverse group of participants, who collaborated to develop a variety of impressive projects based on:
1205
Participants
46
Teams
7
AI Applications
Winners and Finalists
- We are in the process of selecting the finalist teams.
- Your voice matters! Vote on your favorite projects in the section below.
- Join us for the winner announcement stream, which will be streamed live on Twitch.
LLM-based hierarchical data extraction
LLM allow to extract features from their own parameters in a hierarchical way. This in turn allows to improve ML algorithms such as object recognition, but also reduce LLM's size and training time in the future with new architectures.
NoLimits
Gaia Mini Med
"Introducing Gaia Mini Med, an innovative fine-tuned model derived from cutting-edge data sources. Gaia's superior performance stems from its advanced training methodology, surpassing other falcon fine-tunes in accuracy and effectiveness."
Team Tonic
DOR summarizing tool
AI tool that can read and summarize recurring Daily operation reports (DOR) used by natural resource extraction companies.
Green lamp
Falcon Barsita
Falcon Barista is a proof of concept (POC) of an order-taking bot with speech capabilities. It can converse with customers and take their orders in a coffee shop or any restaurant, potentially saving labor costs for the restaurant industry.
Deep Dream
Speakers, Mentors, and Organizers
.png&w=3840&q=75)
Shebagi Mitra
Student
Haneen Salih
Community Manager
Dina Shall
Global Community Manager
.png&w=3840&q=75)
Muhammad Inaam
.png&w=3840&q=75)
Iga Romowska
alsu5
This event has now ended, but you can still register for upcoming events on lablab.ai. We look forward to seeing you at the next one!
Checkout Upcoming Events →Submitted Concepts, Prototypes and Pitches
Submissions from the teams participating in the Falcon LLMs Hackathon sponsored by GAIA event and making it to the end 👊
ECOMMERCE Assistant
A courteous and versatile multimodal chatbot, equipped with sentiment analysis capabilities, excels in responding to user inquiries, providing valuable information, and facilitating a smooth and enjoyable shopping experience.
FutureTech Mavericks
Falcon Document Parser
The document parsing application leverages Falcon LLM to accurately extract data from invoices, aiming to boost efficiency, save valuable time, and minimize manual errors, providing a streamlined and reliable solution for various business needs.
FalconBytes
DOR summarizing tool
AI tool that can read and summarize recurring Daily operation reports (DOR) used by natural resource extraction companies.
Green lamp
Gaia Mini Med
"Introducing Gaia Mini Med, an innovative fine-tuned model derived from cutting-edge data sources. Gaia's superior performance stems from its advanced training methodology, surpassing other falcon fine-tunes in accuracy and effectiveness."
Team Tonic
AiLingo-your personalized language speaking coach
We specialize in the application of LLM within educational delivery, especially in the context of one-on-one, real-time, and personalized language learning platforms. Individuals can send voice messages to an AI respondent in various scenarios.
Ailingo
Falcon Barsita
Falcon Barista is a proof of concept (POC) of an order-taking bot with speech capabilities. It can converse with customers and take their orders in a coffee shop or any restaurant, potentially saving labor costs for the restaurant industry.
Deep Dream
LLM-based hierarchical data extraction
LLM allow to extract features from their own parameters in a hierarchical way. This in turn allows to improve ML algorithms such as object recognition, but also reduce LLM's size and training time in the future with new architectures.
NoLimits