Search-o1: Agentic Search-Enhanced Large Reasoning Models

Arena-Hard-Auto: An automatic LLM benchmark.

SuperCLUE: 中文通用大模型综合性基准 | A Benchmark for Foundation Models in Chinese

Virtual whiteboard for sketching hand-drawn like diagrams

🧡 Follow everything in one place

Official inference framework for 1-bit LLMs

g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains

An incremental parsing system for programming tools

Distribute and run LLMs with a single file.

a QA tool to random generate sql by bnf pattern

Generative AI extensions for onnxruntime

A high-throughput and memory-efficient inference and serving engine for LLMs

Open-Sora: Democratizing Efficient Video Production for All

Grok open release

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

Interact with your documents using the power of GPT, 100% privately, no data leaks

The Memory layer for AI Agents

text2vec, text to vector. 文本向量表征工具，把文本转化为向量矩阵，实现了Word2Vec、RankBM25、Sentence-BERT、CoSENT等文本表征、文本相似度计算模型，开箱即用。

High-speed Large Language Model Serving for Local Deployment

leaked prompts of GPTs

Example models using DeepSpeed

Semantic Evaluation for Text-to-SQL with Distilled Test Suites

A collection of GPT system prompts and various prompt injection/leaking knowledge.

Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)

Crawl a site to generate knowledge files to create your own custom GPT from a URL

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficie…

Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)

Fast and memory-efficient exact attention

LLM inference in C/C++