Stars
Code and data used in the paper: "Training on Incorrect Synthetic Data via RL Scales LLM Math Reasoning Eight-Fold"
Agentless🐱: an agentless approach to automatically solve software development problems
Fast and memory-efficient exact attention
aider is AI pair programming in your terminal
llama3 implementation one matrix multiplication at a time
[ACL 2024] Exploring Safety Generalization Challenges of Large Language Models via Code
A project structure aware autonomous software engineer aiming for autonomous program improvement. Resolved 30.67% tasks (pass@1) in SWE-bench lite and 38.40% tasks (pass@1) in SWE-bench verified wi…
🐙 OctoPack: Instruction Tuning Code Large Language Models
An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)
OpenMMLab Foundational Library for Training Deep Learning Models
SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.
Official release of InternLM2.5 base and chat models. 1M context support
[ICLR 2024] SWE-Bench: Can Language Models Resolve Real-world Github Issues?
A Comprehensive Benchmark for Software Development.
算法面试必备，推荐刷题网站www.lintcode.com。北大学霸的《LeetCode刷题模板》+V领取: jiuzhangfeifei
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
A high-throughput and memory-efficient inference and serving engine for LLMs
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
JsonTuning: Towards Generalizable, Robust, and Controllable Instruction Tuning
A quick guide (especially) for trending instruction finetuning datasets
A framework for few-shot evaluation of language models.
DeepSeek Coder: Let the Code Write Itself
A curation of awesome tools, documents and projects about LLM Security.