Stars
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
LegalOne: A Family of Foundation Models for Reliable Legal Reasoning
Next paradigm for LLM Agent. Unify plan and action through recursive code generation for adaptive, human-like decision-making.
An evaluation framework to test AI in a trial-and-error process. It is a simplified Natural Selection test.
The official repo for paper, LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods.
BlinkDL / nanoRWKV
Forked from karpathy/nanoGPTRWKV in nanoGPT style
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…
Simple, minimal implementation of the Mamba SSM in one file of PyTorch.
⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)
[SIGIR 2023] This is the official PyTorch implementation for the paper: "EulerNet: Adaptive Feature Interaction Learning via Euler’s Formula for CTR Prediction".
RUCAIBox / EulerNet
Forked from Ethan-TZ/EulerNetThis is the official PyTorch implementation for the paper: "EulerNet: Adaptive Feature Interaction Learning via Euler’s Formula for CTR Prediction".
A series of large language models developed by Baichuan Intelligent Technology
🕹️ A basic gameboy emulator with terminal "Cloud Gaming" support
Build, evaluate, understand, and fix LLM-based apps
deepspeed+trainer简单高效实现多卡微调大模型
T2Ranking: A large-scale Chinese benchmark for passage ranking.
Code to reproduce THUIR‘s submissions for COLIEE 2023 Task1 and Task2
The official repo for our SIGIR'23 Full paper: Constructing Tree-based Index for Efficient and Effective Dense Retrieval
The official repo for our SIGIR'23 Full paper: Structure-aware Pre-trained Language Model for Legal Case Retrieval
ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型
Instruct-tune LLaMA on consumer hardware
Making large AI models cheaper, faster and more accessible