Repository for PrimeVul Vulnerability Detection Dataset

Qwen2.5-Coder is the code version of Qwen2.5, the large language model series developed by Qwen team, Alibaba Cloud.

Replication package for FastFixer: An Efficient and Effective Approach for Repairing Programming Assignments

[TMLR] A curated list of language modeling researches for code (and other software engineering activities), plus related datasets.

Model interpretability and understanding for PyTorch

Find dead Python code

📰 Must-read papers and blogs on Speculative Decoding ⚡️

✨ RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems - ICLR 2024

Repository of the paper "Accelerating Transformer Inference for Translation via Parallel Decoding"

Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"

contrastive decoding

CLuster And RepAir tool for introductory programming assignments

Platform to experiment with the AI Software Engineer. Terminal based. NOTE: Very different from https://gptengineer.app

[ICML 2023] Data and code release for the paper "DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation".

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

Code and documentation to train Stanford's Alpaca models, and generate the data.

Detect hallucinated tokens for conditional sequence generation.

Inference code for Llama models

Instruct-tune LLaMA on consumer hardware

Code for the paper "A Structural Model for Contextual Code Changes"

Training language models to make programs faster

A bug repository that keeps growing

Extract GitHub repositories metadata and README content.