Qoboty

Qoboty's Stars

• janhq/jan

  Jan is an open source alternative to ChatGPT that runs 100% offline on your computer. Multiple engine support (llama.cpp, TensorRT-LLM)

  Language:TypeScript23.7k1341.9k1.4k

• unslothai/unsloth

  Finetune Llama 3.2, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 80% less memory

  Language:Python18.5k1291k1.3k

• exo-explore/exo

  Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

  Language:Python15.9k112301844

• geekyutao/Inpaint-Anything

  Inpaint anything using Segment Anything and inpainting models.

  Language:Jupyter Notebook6.6k53150549

• FunAudioLLM/CosyVoice

  Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

  Language:Python6.5k65540698

• google/gemma.cpp

  lightweight, standalone C++ inference engine for Google's Gemma models.

  Language:C++6k3988509

• allenai/OLMo

  Modeling, training, eval, and inference code for OLMo

  Language:Python4.7k47199480

• GuijiAI/duix.ai

  Language:C++4.4k21441651

• snakers4/silero-vad

  Silero VAD: pre-trained enterprise-grade Voice Activity Detector

  Language:Python4.4k49244432

• modelscope/ms-swift

  Use PEFT or Full-parameter to finetune 400+ LLMs or 100+ MLLMs. (LLM: Qwen2.5, Llama3.2, GLM4, Internlm2.5, Yi1.5, Mistral, Baichuan2, DeepSeek, Gemma2, ...; MLLM: Qwen2-VL, Qwen2-Audio, Llama3.2-Vision, Llava, InternVL2, MiniCPM-V-2.6, GLM4v, Xcomposer2.5, Yi-VL, DeepSeek-VL, Phi3.5-Vision, ...)

  Language:Python4.4k221.3k385

• collabora/WhisperSpeech

  An Open Source text-to-speech system built by inverting Whisper.

  Language:Jupyter Notebook4k76112216

• Kwai-Kolors/Kolors

  Kolors Team

  Language:Python3.9k38138274

• AnswerDotAI/gpu.cpp

  A lightweight library for portable low-level GPU computation using WebGPU.

  Language:C++3.8k4724177

• karpathy/build-nanogpt

  Video+code lecture on building nanoGPT from scratch

  Language:Python3.6k3721504

• pipecat-ai/pipecat

  Open Source framework for voice and multimodal conversational AI

  Language:Python3.4k27154334

• cambrian-mllm/cambrian

  Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

  Language:Python1.8k2169115

• fixie-ai/ultravox

  A fast multimodal LLM for real-time voice

  Language:Python1.4k334588

• karpathy/nano-llama31

  nanoGPT style version of Llama 3.1

  Language:Python1.2k23663

• QwenLM/Qwen2-Audio

  The official repo of Qwen2-Audio chat & pretrained large audio language model proposed by Alibaba Cloud.

  Language:Python1.2k328184

• facebookresearch/MobileLLM

  MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.

  Language:Python1.2k221165

• mlfoundations/dclm

  DataComp for Language Models

  Language:HTML1.2k3863107

• bytedance/SALMONN

  SALMONN: Speech Audio Language Music Open Neural Network

  Language:Python1.1k266283

• showlab/Show-o

  Repository for Show-o, One Single Transformer to Unify Multimodal Understanding and Generation.

  Language:Python1k144644

• ricky0123/vad

  Voice activity detector (VAD) for the browser with a simple API

  Language:TypeScript90211100143

• multimodal-art-projection/MAP-NEO

  Language:Python880113482

• jishengpeng/WavTokenizer

  SOTA discrete acoustic codec models with 40 tokens per second for audio language modeling

  Language:Python797205043

• liutaocode/TTS-arxiv-daily

  Automatically Update Text-to-speech (TTS) Papers Daily using Github Actions (Update Every 12th hours)

  Language:Python29041021

• Pints-AI/1.5-Pints

  A compact LLM pretrained in 9 days by using high quality data

  Language:Python2665620

• homebrewltd/llama3-s

  Llama3.1 learns to Listen

  Language:Python1485295

• frankyoujian/Edge-Punct-Casing

  Language:Python17333