eisenzopf

eisenzopf's Stars

• THUDM/LongBench

  LongBench v2 and LongBench (ACL 2024)

  Language:Python71560

• center-for-humans-and-machines/transformer-heads

  Toolkit for attaching, training, saving and loading of new heads for transformer models

  Language:Jupyter Notebook25422

• hiyouga/LLaMA-Factory

  Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

  Language:Python36.9k4.5k

• jiaweizzhao/GaLore

  GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

  Language:Python1.5k154

• qdrant/qdrant

  Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

  Language:Rust21.1k1.4k

• urchade/GLiNER

  Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts) @ NAACL 2024

  Language:Python1.6k141

• xai-org/grok-1

  Grok open release

  Language:Python49.8k8.3k

• stanfordnlp/dspy

  DSPy: The framework for programming—not prompting—language models

  Language:Python20.5k1.6k

• sanchit-gandhi/notebooks

  A collection of notebooks for the Hugging Face blog series (https://huggingface.co/blog).

  Language:Jupyter Notebook425

• bevyengine/bevy

  A refreshingly simple data-driven game engine built in Rust

  Language:Rust37.2k3.7k

• NVIDIA/TensorRT-LLM

  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 efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

  Language:C++9k1k

• eeroel/hae

  Like grep but with natural language queries

  Language:C++48

• PolyAI-LDN/pheme

  Language:Python25425

• coqui-ai/TTS

  🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

  Language:Python36.4k4.5k

• DagsHub/audio-datasets

  open-source audio datasets

  14424

• Kyubyong/css10

  CSS10: A Collection of Single Speaker Speech Datasets for 10 Languages

  Language:HTML46860

• myshell-ai/OpenVoice

  Instant voice cloning by MIT and MyShell.

  Language:Python30.2k3k

• anakin87/mistral-haystack

  Mistral + Haystack: build RAG pipelines that rock 🤘

  Language:Jupyter Notebook10010

• SJTU-IPADS/PowerInfer

  High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

  Language:C++8k418

• neulab/prompt2model

  prompt2model - Generate Deployable Models from Natural Language Instructions

  Language:Python2k177

• mlabonne/llm-course

  Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

  Language:Jupyter Notebook40.4k4.3k

• shreyaskarnik/DistiLlama

  Chrome Extension to Summarize or Chat with Web Pages/Local Documents Using locally running LLMs. Keep all of your data and conversations private. 🔐

  Language:TypeScript28630

• snipsco/snips-nlu-parsers

  Rust crate for entity parsing

  Language:Rust1632

• speechbrain/speechbrain

  A PyTorch-based Speech Toolkit

  Language:Python9.1k1.4k

• huggingface/alignment-handbook

  Robust recipes to align language models with human and AI preferences

  Language:Python4.8k420

• housleyjk/ws-rs

  Lightweight, event-driven WebSockets for Rust.

  Language:Rust1.5k222

• tigerlab-ai/tiger

  Open Source LLM toolkit to build trustworthy LLM applications. TigerArmor (AI safety), TigerRAG (embedding, RAG), TigerTune (fine-tuning)

  Language:Jupyter Notebook39026

• microsoft/autogen

  A programming framework for agentic AI 🤖 PyPi: autogen-agentchat Discord: https://aka.ms/autogen-discord Office Hour: https://aka.ms/autogen-officehour

  Language:Jupyter Notebook36.4k5.3k

• FL33TW00D/whisper-turbo

  Cross-Platform, GPU Accelerated Whisper 🏎️

  Language:TypeScript1.8k79

• m-bain/whisperX

  WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

  Language:Python13k1.4k