gatepoet

gatepoet's Stars

• google-ai-edge/mediapipe

  Cross-platform, customizable ML solutions for live and streaming media.

  Language:C++26.6k4985.1k5.1k

• microsoft/JARVIS

  JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

  Language:Python23.5k3841772k

• guidance-ai/guidance

  A guidance language for controlling large language models.

  Language:Jupyter Notebook18.6k1165191k

• sweepai/sweep

  Sweep: open-source AI-powered Software Developer for small features and bug fixes.

  Language:Jupyter Notebook7.4k43916420

• ijl/orjson

  Fast, correct Python JSON library supporting dataclasses, datetimes, and numpy

  Language:Python6k36414209

• microsoft/LLMLingua

  To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

  Language:Python4.4k32112240

• huggingface/parler-tts

  Inference and training library for high-quality TTS models.

  Language:Python4k5587398

• mshumer/gpt-llm-trainer

  Language:Jupyter Notebook3.9k6922505

• OpenNMT/CTranslate2

  Fast inference engine for Transformer models

  Language:C++3.2k56675281

• KoljaB/RealtimeSTT

  A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.

  Language:Python1.5k2573141

• trypromptly/LLMStack

  No-code multi-agent framework to build LLM Agents, workflows and applications with your data

  Language:Python1.4k1943211

• FoundationVision/LlamaGen

  Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

  Language:Python1.2k215245

• punica-ai/punica

  Serving multiple LoRA finetuned LLM as one

  Language:Python934123842

• TransformerOptimus/SuperCoder

  Open Source Autonomous Software Development System

  Language:Go700123658

• PrithivirajDamodaran/FlashRank

  Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & Collaborations.

  Language:Python54162442

• KoljaB/LocalAIVoiceChat

  Local AI talk with a custom voice based on Zephyr 7B model. Uses RealtimeSTT with faster_whisper for transcription and RealtimeTTS with Coqui XTTS for synthesis.

  Language:Python45991247

• chujiezheng/chat_templates

  Chat Templates for 🤗 HuggingFace Large Language Models

  Language:Jinja42961140

• varunshenoy/super-json-mode

  Low latency JSON generation using LLMs ⚡️

  Language:Jupyter Notebook3782512

• KoljaB/Linguflex

  Command Your World with Voice

  Language:Python3449841

• matatonic/openedai-speech

  An OpenAI API compatible text to speech server using Coqui AI's xtts_v2 and/or piper tts as the backend.

  Language:Python27684041

• microsoft/Trace

  Trace, the New AutoDiff for AI Systems and LLM Agents

  Language:Python2497414

• microsoft/sarathi-serve

  A low-latency & high-throughput serving engine for LLMs

  Language:Python15951222

• SakanaAI/DiscoPOP

  Code for Discovering Preference Optimization Algorithms with and for Large Language Models

  Language:Python1544017

• jundaf2/INT8-Flash-Attention-FMHA-Quantization

  Language:Cuda1505516

• lunamidori5/Midori-AI

  894923

• crashr/gppm

  GPU Power and Performance Manager

  Language:Python36314

• KoljaB/stream2sentence

  Real-time processing and delivery of sentences from a continuous stream of characters or text chunks.

  Language:Python27216

• LLMparser/LLMparser

  Language:Python12212

• JamesHutchison/learning-progressions

  Use GPT-4 to create learning progressions

  Language:Python1100

• PrithivirajDamodaran/beir

  A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.

  Language:Python1