Name: Chris Poulin
Type: User
Company: Patterns and Predictions
Bio: Chris Poulin is a research scientist and managing partner at Patterns and Predictions, a predictive analytics group.
Twitter: cdpoulin
Location: Boston & Palo Alto
Blog: https://predictus.com
Chris Poulin's Projects
DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
Deep Reinforcement Learning Agent
fabric is an open-source framework for augmenting humans using AI. It provides a modular framework for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.
Generative Models by Stability AI
A framework for Claude Opus to intelligently orchestrate subagents.
The MATH Dataset (NeurIPS 2021)
Implementation of Nvidia's NeuralPlexer, for end-to-end differentiable design of functional small-molecules and ligand-binding proteins, in Pytorch
An Easy-to-use, Scalable and High-performance RLHF Framework (Support 70B+ full tuning & LoRA & Mixtral & KTO)
A library for building fast, reliable and evolvable network services.
800,000 step-level correctness labels on LLM solutions to MATH problems
Code for "ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning" (ICLR 2020)
The RedPajama-Data repository contains code for preparing large datasets for training large language models.
Reverb is an efficient and easy-to-use data storage and transport system designed for machine learning research
Data and code for NeurIPS 2022 Paper "Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering".
Concept Sliders for Precise Control of Diffusion Models
SDK for interacting with stability.ai APIs (e.g. stable diffusion inference)
From Stable Diffusion
High-Resolution Image Synthesis with Latent Diffusion Models
StableLM: Stability AI Language Models
Community interface for generative AI
StableSwarmUI, A Modular Stable Diffusion Web-User-Interface, with an emphasis on making powertools easily accessible, high performance, and extensibility.
The dataset and code for paper: TheoremQA: A Theorem-driven Question Answering dataset
A minimal GPU design in Verilog to learn how GPUs work from the ground up