Lists (1)
Stars
Structural Reasoning About Program Correctness in Natural Language
The official implementation of "Self-play LLM Theorem Provers with Iterative Conjecturing and Proving"
ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools [ICLR'24].
A Seamless, Interactive Tactic Learner and Prover for Coq
verl: Volcano Engine Reinforcement Learning for LLMs
An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)
Fully open reproduction of DeepSeek-R1
[TMLR] A curated list of language modeling researches for code (and other software engineering activities), plus related datasets.
Minimal reproduction of DeepSeek R1-Zero
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)
Qwen2.5-Coder is the code version of Qwen2.5, the large language model series developed by Qwen team, Alibaba Cloud.
DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
[ICML'24] Magicoder: Empowering Code Generation with OSS-Instruct
This is the official code for the paper CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning (NeurIPS22).
👨💻 An awesome and curated list of best code-LLM for research.
Universal Online Judge (Community Edition)
DeepSeek Coder: Let the Code Write Itself
Python wrapper for the Mahjong Soul (Majsoul) Protobuf objects. It allows to use their API.
Production-ready platform for agentic workflow development.
Code for the paper "Evaluating Large Language Models Trained on Code"
Code2Inv: Learning Loop Invariants for Program Verification
Code for the paper "LLM Meets Bounded Model Checking: Neuro-symbolic Loop Invariant Inference" at ASE 2024
A collection of recent papers, benchmarks and datasets of AI4Code domain.
Ranking LLM-Generated Loop Invariants for Program Verification.