Jiaxin-Wen

OpenDevin

🐚 OpenDevin: Code Less, Make More

cv

Print-friendly, minimalist CV page

FriendsDontLetFriends

Friends don't let friends make certain types of data visualization - What are they and why are they bad.

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

gemma_pytorch

The official PyTorch implementation of Google's Gemma models

MiniCPM

MiniCPM-2B: An end-side LLM outperforming Llama2-13B.

OLMo

Modeling, training, eval, and inference code for OLMo

alphageometry

shareOI

算法竞赛课件分享

Qwen1.5

Qwen1.5 is the improved version of Qwen, the large language model series developed by Qwen team, Alibaba Cloud.

AlphaCodium

Official implementation for the paper: "Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering""

llm-attacks

Universal and Transferable Attacks on Aligned Language Models

mamba-minimal

Simple, minimal implementation of the Mamba SSM in one file of PyTorch.

weak-to-strong

chinese-llm-benchmark

中文大模型能力评测榜单：目前已囊括106个大模型，覆盖chatgpt、gpt4o、百度文心一言、阿里通义千问、讯飞星火、商汤senseChat、minimax等商用模型， 以及百川、qwen2、glm4、yi、书生internLM2、llama3等开源大模型，多维度能力评测。不仅提供能力评分排行榜，也提供所有模型的原始输出结果！

Minigrid

Simple and easily configurable grid world environments for reinforcement learning

mysupervisor_save

收集“导师评价”相关资源，及原“导师评价网”存档数据

open-instruct

evalplus

Rigourous evaluation of LLM-synthesized code - NeurIPS 2023

DeepSeek-MoE

DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

babyai

BabyAI platform. A testbed for training agents to understand and execute language commands.

MathPile

Generative AI for Math: MathPile

llamafia.github

HarmBench

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

FineGrainedRLHF

Thought-Cloning

[NeurIPS '23 Spotlight] Thought Cloning: Learning to Think while Acting by Imitating Human Thinking

intercode

[NeurIPS 2023 D&B] Code repository for InterCode benchmark https://arxiv.org/abs/2306.14898

WechatAnnualReport

微信聊天记录导出、微信年度报告生成！记录你的2023！

OlympiadBench

[ACL 2024]Official GitHub repo for OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems.

fneval

Functional Benchmarks and the Reasoning Gap