Real-Time Open-Vocabulary Object Detection

Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with …

The Go programming language

A generative speech model for daily dialogue.

The official gpt4free repository | various collection of powerful language models

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

中文羊驼大模型三期项目 (Chinese Llama-3 LLMs) developed from Meta Llama 3

Flutter makes it easy and fast to build beautiful apps for mobile and beyond

XTuner is a toolkit for efficiently fine-tuning LLM

Microsoft Automatic Mixed Precision Library

a state-of-the-art-level open visual language model | 多模态预训练模型

Building your own video generation model like OpenAI's Sora

This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!

Port of Facebook's LLaMA model in C/C++

An open source implementation of CLIP.

中文LLaMA-2 & Alpaca-2大模型二期项目 + 16K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs, including 16K long context models)

OpenBLAS is an optimized BLAS library based on GotoBLAS2 1.13 BSD version.

Inference Llama 2 in one file of pure C

纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行

Llama中文社区，最好的中文Llama大模型，完全开源可商用

InternLM has open-sourced a 7 and 20 billion parameter base models and chat models tailored for practical scenarios and the training system.

Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

Public repo for HF blog posts

Code for the paper "Rethinking Benchmark and Contamination for Language Models with Rephrased Samples"

A batched offline inference oriented version of segment-anything

Official Implementation of "Frozen Transformers in Language Models are Effective Visual Encoder Layers"

Evaluating LLMs' multi-round chatting capability via assessing conversations generated by two LLM instances.

Simple Implementation of Pix2seqV2(multi-task)