Stars
[ICLR 2025 Oral] Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows
[arXiv] Official Repository for the Paper "SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning"
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agent RL)
Blender 3DGS & 4DGS Viewer Nodes developed by Mediastorm, with basic rendering styles for quick inspection.
Benchmarking long-form factuality in large language models. Original code for our paper "Long-form factuality in large language models".
RooCodeInc / Roo-Code
Forked from cline/clineRoo Code (prev. Roo Cline) gives you a whole dev team of AI agents in your code editor.
π Make websites accessible for AI agents. Automate tasks online with ease.
Convert PDF to markdown + JSON quickly with high accuracy
A Conversational Speech Generation Model
Unleash Next-Level AI! π π» Code Generation: DeepSeek r1 + Claude 3.7 Sonnet - Unparalleled Performance! π Content Creation: DeepSeek r1 + Gemini 2.5 Pro - Superior Quality! π OpenAI-Compatible. π Sβ¦
Command & Conquer: Remastered Collection
SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.
Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML
Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
GGUF Quantization support for native ComfyUI models
Hot is macOS menu bar application that displays the CPU speed limit due to thermal issues.
A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
Fine-tuning & Reinforcement Learning for LLMs. π¦₯ Train Qwen3, Llama 4, DeepSeek-R1, Gemma 3, TTS 2x faster with 70% less VRAM.
A collection of prompts to challenge the reasoning abilities of large language models in presence of misguiding information
Implements harmful/harmless refusal removal using pure HF Transformers
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
We are committed to the open-sourcing quantitative knowledge, aiming to bridge the information gap between the domestic and international quantitative finance industries. ζ们θ΄εδΊιεη₯θ―ηεΌζΊδΈζ±εοΌζη ΄ε½ε ε€ιειθθ‘β¦
Create Epic Math and Physics Animations From Text.
verl: Volcano Engine Reinforcement Learning for LLMs
DeepBattler - Your BEST LLM Battlegrounds Coach/FriendοΌ
zero-peak / ZeroOmega
Forked from FelisCatus/SwitchyOmegaManage and switch between multiple proxies quickly & easily.