Finetune Llama 3.3, Mistral, Phi-4, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory

Janus-Series: Unified Multimodal Understanding and Generation Models

PySonar2: a semantic indexer for Python with interprocedual type inference

Pretty good call graphs for dynamic languages

This is a network framework based on command mode. No need to manage thread/socket yourself... Contains subsyst

Run generative AI models in sophgo BM1684X

心理健康大模型、LLM、The Big Model of Mental Health、Finetune、InternLM2、InternLM2.5、Qwen、ChatGLM、Baichuan、DeepSeek、Mixtral、LLama3、GLM4、Qwen2、LLama3.1

[CVPR 2024] Official implementation of the paper "Visual In-context Learning"

[ECCV2024] API code for T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy

A collection of modern/faster/saner alternatives to common unix commands.

Scalable RL solution for advanced reasoning of language models

Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba

Automatic integrate all Xiaomi devices to HomeAssistant via miot-spec, support Wi-Fi, BLE, ZigBee devices. 小米米家智能家居设备接入Hass集成

Feature-rich wifi hotspot creator for Linux which provides both GUI and command-line interface. It is also able to create a hotspot using the same wifi card which is connected to an AP already ( Si…

Machine Learning Engineering Open Book

Flops counter for convolutional networks in pytorch framework

Official implementation for "Android in the Zoo: Chain-of-Action-Thought for GUI Agents" (Findings of EMNLP 2024)

Google Research

The “Quite OK Image Format” for fast, lossless image compression

Embedded graphics library to create beautiful UIs for any MCU, MPU and display type.

🚀🚀 「大模型」3小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 3 hours!

🚀 「大模型」3小时从0训练27M参数的视觉多模态VLM！🌏 Train a 27M-parameter VLM from scratch in just 3 hours!

[ACL 2024 Demo] Official GitHub repo for UltraEval: An open source framework for evaluating foundation models.

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

🎬 卡卡字幕助手 | VideoCaptioner - 基于 LLM 的智能字幕助手，无需GPU一键高质量字幕视频合成！视频字幕生成、断句、校正、字幕翻译全流程。让字幕制作简单高效！

faster_whisper GUI with PySide6

Netflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team | Netflix级字幕切割、翻译、对齐、甚至加上配音，一键全自动视频搬运AI字幕组

Got: Simple golang package and CLI tool to download large files faster 🏃 than cURL and Wget!