johncollinsai Goto Github PK
Name: John Collins, PhD
Type: User
Company: Deep Vertical AI
Bio: Founder at Deep Vertical AI
Location: Singapore
Blog: deepvertical.ai
Name: John Collins, PhD
Type: User
Company: Deep Vertical AI
Bio: Founder at Deep Vertical AI
Location: Singapore
Blog: deepvertical.ai
GPT4 Chatbot app featuring different analysis modalities. Model: OpenAI GPT-4. Frontend: Flask, HTML, CSS, and JavaScript. Fetch API: Asynchronous data fetching and communication. pdf-lib: PDF generation/manipulation in the browser. K8s and nginx on GKE.
"Analyst" GPT app using GPT4 and text-davinci-003. Explores impact of prompt engineering. Written in Python, using OpenAI APIs. Implemented as a web app with Python Flask framework and blueprint factory structure, Java Script, Bootstrap, CSS, and HTML. Hosted on GCP.
The prime focus of my codellama project is to fine-tune the Code Llama 7B model and juxtapose its performance with GPT-4. Utilizing the stack outlined in README, I dive into an extensive analysis, providing a robust framework for further work with the Code Llama model.
In this post I discuss some of the academic papers I have read and found useful when considering deep learning in general, and specifically its application in finance. Identical post to https://github.com/johncollinsai/dlf, but here implemented via Voila.
In this post I discuss some of the academic papers I have read and found useful when considering deep learning in general, and specifically its application in finance. Implemented here via Flask.
Fine-tuning of language models and prompt engineering, using the problem setting of stock price prediction based on high-frequency OHLC stock price data for AAPL.Training gpt-3.5-turbo on OHLC data to obtain raw return and log return predictions.
repo for GPT4 post
This is the website created by GPT4, as part of my post GPT4
Webapp for showcasing an AI chatbot. Greg allows a complex chatbot to be handled as a separate microservice. My project AnalystGPT (ai-analystgpt) is the chatbot microservice (note use of separate node.js email service within ai-analystgpt).
Preparation of high frequency tick-by-tick OHLC datasets from NYSE TAQ for AAPL, JPM, and EURUSD. Python code, extended Jupyter notebook writeup. Deployed on GCP via GKE.
This post is an abridged version of a paper I wrote some time ago and provides a thorough derivation of the LSTM network, something often skipped in finance DL papers.
Python implementation of the Markov-Switching Multifractal model (MSM) of Calvet & Fisher (2004, 2008).
Implementation of Karpathy's NanoGPT
Explores prompt engineering constructs. Python completions from GPT-4 using OpenAI API. Frontend: Flask, HTML, CSS, and JavaScript. Fetch API: Asynchronous data fetching and communication with the server. Deployed on gcloud as Cloud Run service.
Prompt Evolution uses an iterative process to evolve better prompts for a domain, in this case project management of AI initiatives. As described in "Promptbreeder" (Fernando et al., 2023), it leverages a language model to generate variations of prompts, evaluates their utility, and selects the most useful prompts to propogate to next generation.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.