Official repository for ORPO

This is a Phi-3 book for getting started with Phi-3. Phi-3, a family of open AI models developed by Microsoft. Phi-3 models are the most capable and cost-effective small language models (SLMs) avai…

The repository contains the code and dataset for the Socratic Debugging task which is a novel task for Socratically Questioning Novice Debuggers to guide them towards discovering and fixing a buggy…

Gen-Ed is a framework for building web applications that use generative AI (LLMs) for education.

This repository contains some LLM deployment examples

[ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diverse strengths of multiple open-source LLMs. LLM-Blender cut …

Refactory: Re-factoring based Program Repair applied to Programming Assignments

Codabench is a flexible, easy-to-use and reproducible benchmarking platform. Check our paper at Patterns Cell Press https://hubs.li/Q01fwRWB0

CodeTF: One-stop Transformer Library for State-of-the-art Code LLM

Code for Open-ended Knowledge Tracing

Tool to parse Python code

Inference code for Llama models

The MATH Dataset (NeurIPS 2021)

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,…

Open Source Intelligent Tutoring System w/ BKT (ReactJS and Firebase)

Generates questions about constructs and patterns in a given program

pyKT: A Python Library to Benchmark Deep Learning based Knowledge Tracing Models

A scikit-learn compatible neural network library that wraps PyTorch

Efficient implementations for handling large-scale student log data and knowledge tracing algorithms.

A collection of modular datasets generated by GPT-4, General-Instruct - Roleplay-Instruct - Code-Instruct - and Toolformer

Generative model for code infilling and synthesis

Code for generating the JuICe dataset.

StaQC: a systematically mined dataset containing around 148K Python and 120K SQL domain question-code pairs, as described in "StaQC: A Systematically Mined Question-Code Dataset from Stack Overflow…

Python modules for program embeddings computation