Reverse Dependencies of accelerate
The following projects have a declared dependency on accelerate:
- soundstorm-pytorch — SoundStorm - Efficient Parallel Audio Generation from Google Deepmind, in Pytorch
- soundstorm-superfeel — SoundStorm - Efficient Parallel Audio Generation from Google Deepmind, in Pytorch
- spadepp — no summary
- span-marker — Named Entity Recognition using Span Markers
- sparseml — Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models
- sparseml-nightly — Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models
- speakerchangedetect — A Package to Detect Speaker Change based on Textual Features via LLMs & Rule-Based NLP and Audio Features via Pyannote & Spectral Clustering
- speechbox — Speechbox
- speechlib — speechlib is a library that can do speaker diarization, transcription and speaker recognition on an audio file to create transcripts with actual speaker names. This library also contain audio preprocessor functions.
- spender — Spectrum encoder and decoder
- spice-agent — spice agent
- sqlgym — SQLGym: A portable Gymnasium environment of SQLite database.
- stablefused — StableFused is a toy library to experiment with Stable Diffusion inspired by 🤗 diffusers and various other sources!
- stablefusion — StableFusion
- stablepy — A tool for easy use of stable diffusion
- starlight-vision — Starlight - unprecedented photorealism × deep level of language understanding
- statecraft — Store, manage and remix states for SSMs and other Stateful models
- stf-test1 — stf
- STFD — STFD: Series of deep learning-based foundation models for spatial transcriptomic data analysis
- stochasticx — Stochastic client library
- stonkgs — Sophisticated Transformers for Biomedical Text and Knowledge Graph Data
- strategais — A Python library for deploying large language models (LLMs) in local environments.
- streamdiffusion — real-time interactive image generation pipeline
- studcamp-yandex-hse — Text-tagging project within Yandex x HSE StudCamp event
- stuned — Utility code from STAI (https://scalabletrustworthyai.github.io/)
- styletts2 — StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models. Original authors: Yinghao Aaron Li, Cong Han, Vinay S. Raghavan, Gavin Mischler, Nima Mesgarani.
- styletts2-fork — Fork of StyleTTS 2 Python packge. StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models. Original authors: Yinghao Aaron Li, Cong Han, Vinay S. Raghavan, Gavin Mischler, Nima Mesgarani, Sidharth Rajaram.
- SuperDuperDB — 🔮 Super-power your database with AI 🔮
- superlinked — The Superlinked vector computing library
- svdiff-pytorch — Implementation of 'SVDiff: Compact Parameter Space for Diffusion Fine-Tuning'
- swarmauri — This repository includes core interfaces, standard ABCs and concrete references, third party plugins, and experimental modules for the swarmaURI framework.
- swarms — Swarms - Pytorch
- symbolicai — A Neuro-Symbolic Framework for Python
- tabqa — This Python package provides functions to convert natural language to SQL queries using a pre-trained language model.
- tailors — no summary
- tailwiz — no summary
- taker — Tools for Transformer Activations Knowledge ExtRaction
- tango-extensions — Extension modules for allenai/tango (ai2-tango)
- tango-textual-inversion — allenai/tango version of textual inversion
- tensor-parallel — Automatically shard your large model between multiple GPUs, works without torch.distributed
- test-petals — Easy way to efficiently run 100B+ language models without high-end GPUs
- testfate — no summary
- text-machina — Text Machina: Seamless Generation of Machine-Generated Text Datasets
- text2hologram — Generate holograms from text
- text2text — Text2Text: Crosslingual NLP/G toolkit
- textkit-learn — Helps computers to understand human languages.
- textsum — utility for using transformers summarization models on text docs
- textwiz — An even simpler way to use open-source LLMs.
- tez — tez - a simple pytorch trainer
- tfkit — Transformers kit - Multi-task QA/Tagging/Multi-label Multi-Class Classification/Generation with BERT/ALBERT/T5/BERT
- tgate — T-GATE: Cross-Attention Makes Inference Cumbersome in Text-to-Image Diffusion Models.
- that-nlp-library — Aim to be a convenient NLP library with the help from HuggingFace
- the-grid — Easy way to efficiently run 100B+ language models without high-end GPUs
- thebestllmever — andromeda - Pytorch
- threefiner — Threefiner: a text-guided mesh refiner
- thsquant — A short description of your awesome package
- TimeSeriesML — TimeSeriesML
- tketool — Some base methods for developing
- tldream — A tiny little diffusion drawing app
- TokenProbs — Extract token-level probabilities from LLMs for classification-type outputs.
- torch-frame — 用于深度学习快速实现代码的框架
- torchfitter — Trainer to optimize PyTorch models
- trainer — General purpose model trainer for PyTorch that is more flexible than it should be, by 🐸Coqui.
- trainllm — Fine-tuning LLMs for instruction using QLoRA.
- transformer-lens — An implementation of transformers tailored for mechanistic interpretability.
- transformers — State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow
- transformers-crf — Transformers CRF: CRF Token Classification for Transformers
- transformers-inference-toolkit — A collection of helper methods to simplify optimization and inference of Huggingface Transformers-based models
- transformers-openai-api — An OpenAI Completions API compatible server for NLP transformers models
- transllm — LLMtranslator translates and generates text in multiple languages.
- tril — Transformers Reinforcement and Imitation Learning Library
- trl — Train transformer language models with reinforcement learning.
- tuned-lens — Tools for understanding how transformer predictions are built layer-by-layer
- turkish-lm-tuner — Implementation of the Turkish LM Tuner
- txtai — All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows
- uce-model — Universal Cell Embedding model for single-cell RNA-seq data
- UnBIAS — A package based on LLMs for detecting bias, performing named entity, and debiasing text.
- uniem — unified embedding model
- unipercept — UniPecept: A unified framework for perception tasks focusing on research applications that require a high degree of flexibility and customization.
- unirec — A compact recommender library for universal recommendation systems
- uniteai — AI, Inside your Editor.
- vec2text — convert embedding vectors back to text
- vectara-cli — A CLI tool for interacting with the Vectara platform, including advanced text processing and indexing features.
- vectorlab — A lab for vectors.
- vertex_ai_huggingface_inference_toolkit — 🤗 Hugging Face Inference Toolkit for Google Cloud Vertex AI (similar to SageMaker's Inference Toolkit, but unofficial)
- vfpeft — Parameter-Efficient Fine-Tuning (PEFT)
- viddiffusion — VidDiffusion is a Python library that provides vid2vid pipeline by using Hugging Face's `diffusers`.
- video-transformers — Easiest way of fine-tuning HuggingFace video classification models.
- video2dataset — Easily create large video dataset from video urls
- vietlm — An experiment for large models specific to Vietnamese, including language models and more.
- visualizing-training — Modelling Training Dynamics and Interpreting the dynamics
- vktrs — Video Killed The Radio Star
- vocab-coverage — 语言模型中文识字率分析
- voicebox-pytorch — Voicebox - Pytorch
- wafl-llm — A hybrid chatbot - LLM side.
- weak-annotators — Weak annotators for information extraction (NER)
- whisper-s2t — An Optimized Speech-to-Text Pipeline for the Whisper Model.
- whisperplus — WhisperPlus: A Python library for WhisperPlus API.
- x2vlm-gml — Package for X2-VLM, a vision-language model from ByteDance
- xcube — Extreme Multi-Label Text Classification