luxinyu1

luxinyu1's Stars

• 01-ai/Yi

  A series of large language models trained from scratch by developers @01-ai

  Language:Jupyter Notebook7.7k481

• google-deepmind/tracr

  Language:Python50843

• protagolabs/odyssey-math

  Language:Jupyter Notebook768

• ucl-dark/llm_debate

  Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"

  Language:Python8411

• LantaoYu/MARL-Papers

  Paper list of multi-agent reinforcement learning (MARL)

  4.1k728

• abdulhaim/LMRL-Gym

  Language:Python759

• Linear95/SPAG

  Self-playing Adversarial Language Game Enhances LLM Reasoning, NeurIPS 2024

  Language:Python10011

• google-deepmind/penzai

  A JAX research toolkit for building, editing, and visualizing neural networks.

  Language:Python1.7k53

• teacherpeterpan/self-correction-llm-papers

  This is a collection of research papers for Self-Correcting Large Language Models with Automated Feedback.

  44225

• zchuz/CoT-Reasoning-Survey

  [ACL 2024] A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future

  34912

• opendilab/awesome-RLHF

  A curated list of reinforcement learning with human feedback resources (continually updated)

  3.5k212

• stanford-crfm/ecosystem-graphs

  Language:JavaScript25835

• QwenLM/Qwen2.5

  Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.

  Language:Shell10k620

• Edward-Sun/easy-to-hard

  Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision

  Language:Python9810

• Edward-Sun/gpt-accelera

  Simple and efficient pytorch-native transformer training and inference (batched)

  Language:Python634

• THUDM/AlignBench

  大模型多维度中文对齐评测基准 (ACL 2024)

  Language:Python33525

• open-compass/opencompass

  OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

  Language:Python4.2k449

• xai-org/grok-1

  Grok open release

  Language:Python49.6k8.3k

• princeton-nlp/SWE-bench

  [ICLR 2024] SWE-bench: Can Language Models Resolve Real-world Github Issues?

  Language:Python2k355

• openai/transformer-debugger

  Language:Python4k239

• ArthurConmy/Automatic-Circuit-Discovery

  Language:Jupyter Notebook18837

• openai/democratic-inputs

  Language:HTML5710

• arcee-ai/mergekit

  Tools for merging pretrained large language models.

  Language:Python4.9k445

• conversationai/perspectiveapi

  Perspective is an API that uses machine learning models to score the perceived impact a comment might have on a conversation. See https://developers.perspectiveapi.com for more information.

  892115

• OpenBMB/XAgent

  An Autonomous LLM Agent for Complex Task Solving

  Language:Python8.2k846

• openai/weak-to-strong

  Language:Python2.5k307

• jxzhangjhu/Awesome-LLM-Uncertainty-Reliability-Robustness

  Awesome-LLM-Robustness: a curated list of Uncertainty, Reliability and Robustness in Large Language Models

  67647

• kagisearch/pyllms

  Minimal Python library to connect to LLMs (OpenAI, Anthropic, Google, Groq, Reka, Together, AI21, Cohere, Aleph Alpha, HuggingfaceHub), with a built-in model performance benchmark.

  Language:Python72544

• songquanpeng/one-api

  OpenAI 接口管理 & 分发系统，支持 Azure、Anthropic Claude、Google PaLM 2 & Gemini、智谱 ChatGLM、百度文心一言、讯飞星火认知、阿里通义千问、360 智脑以及腾讯混元，可用于二次分发管理 key，仅单可执行文件，已打包好 Docker 镜像，一键部署，开箱即用. OpenAI key management & redistribution system, using a single API for all LLMs, and features an English UI.

  Language:JavaScript19.5k4.3k

• huggingface/alignment-handbook

  Robust recipes to align language models with human and AI preferences

  Language:Python4.7k414