Cohere Hackathon

Paweł Czech and Mathias Asberg, co-founders of New Native will talk about lablab.ai's mission and vision. https://www.twitch.tv/lablabai

Start

Sharing a broad overview of Cohere, the solutions Cohere provide, tips for the hackathon, Cohere New Multilingual Model and Sandbox 
https://cohere.ai/

Cohere Opening

Together with lablab.ai and Cohere teams we will shortly introduce you to the hackathon challenge and give you the guide for the Hackathon

Introduction to the Challenge, FAQ

Kemi Tijani will introduce you to Cohere and it's technology

Cohere Introduction

Unleash the power of AI with Text Generation! Learn how to generate human-like text with ease, by training models on your own data. 

Getting started with Text Generation

Unlock the power of AI-driven semantic search to improve data discovery & user experience. Learn how to understand intent & context for more accurate results.

Introduction to semantic search

Want to choose the perfect idea for your project? Start by identifying a problem, researching potential solutions, and considering your skills & resources. 

Choose an idea for a project

Ensure long-term success by building a scalable project architecture. Learn best practices to handle growth and adapt to changing requirements.

Build a project architecture to scale

We will be looking for the secret of success with winners of Cohere Hackathon

Panel with Cohere's Winners

Let's get to know each other more and discuss hot topic in AI world during this session

Interviews with participants

Unleashing the power of code to conquer the impossible

The Cyber Savvy Ninjas

Lyam-Katz

Adibvafa Fallahpour

Sung Ha Hwang

Ashleigh Liu

Katrina

There are three essential components in the model: 
‎1. Co:here Classify model that has been trained on almost 500,000 real training data ‎‎(sentence, emotion) and is capable of using NLP to truncate and classify large ‎prompts into a range of emotions. 
‎2. Co:here Embedding + Sklearn model that transforms the user prompt to a list of ‎floats (embeds) and performs semantic search in a massive data base of real, ‎labeled, embedded sentences to find the closest matching example.‎
‎3. Co:here Generate model that receives user input, classified emotions, previous ‎calls, and some hard coded psychological information to generate an accurate ‎therapist response. The model has memory of past inputs and thus can create a ‎coherent conversation.‎
These components work together in the back end, while the front end is a webpage ‎that user can access to send information and read model's responses.‎
Ultimately, the project aims to create an ongoing conversation with Co:DY and user, ‎providing emotional support, helping users work through problems, and offering ‎tailored advice.‎

Co:DY uses advanced LLMs to simulate a conversation between a therapist and user ‎in a webpage setting. It is capable of recognizing emotions, generating relatable ‎response with respect to user input, and giving tailored suggestions and feedback.‎

"The Cyber Savvy Ninjas team on Cohere Hackathon Hackathon"

Team Idea

Submission