-
Peking Univeristy
- Beijing China
-
15:01
(UTC -12:00) - pkuzqh.github.io
- @zqh
Stars
DeepSeek Harness: Everything is a Plugin.
DeepEP: an efficient expert-parallel communication library
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
[ICLR'25] BigCodeBench: Benchmarking Code Generation Towards AGI
The official evaluation suite and dynamic data release for MixEval.
aider is AI pair programming in your terminal
Devika is the first open-source implementation of an Agentic Software Engineer. Initially started as an open-source alternative to Devin.
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
🙌 OpenHands: AI-Driven Development
Code and Data artifact for NeurIPS 2023 paper - "Monitor-Guided Decoding of Code LMs with Static Analysis of Repository Context". `multispy` is a lsp client library in Python intended to be used to…
[ACL 2024]Official GitHub repo for OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems.
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Benchmarking LLMs via Uncertainty Quantification
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
CRUXEval: Code Reasoning, Understanding, and Execution Evaluation
Tools for merging pretrained large language models.
Unofficial Python system monitor and library for small IPS USB-C displays like Turing Smart Screen / TURZX