huggingface / transformersLinks
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
☆146,154Updated this week
Alternatives and similar repositories for transformers
Users that are interested in transformers are comparing it to the libraries listed below
Sorting:
- Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!☆38,779Updated this week
- DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.☆39,142Updated this week
- Facebook AI Research Sequence-to-Sequence Toolkit written in Python.☆31,582Updated 2 weeks ago
- Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.☆29,665Updated this week
- Inference code for Llama models☆58,421Updated 5 months ago
- State-of-the-Art Text Embeddings☆17,024Updated 2 weeks ago
- Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities☆21,441Updated 3 weeks ago
- Unsupervised text tokenizer for Neural Network-based text generation.☆11,022Updated 2 months ago
- A library for efficient similarity search and clustering of dense vectors.☆35,725Updated this week
- 🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools☆20,306Updated this week
- 🦜🔗 Build context-aware reasoning applications☆110,444Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆50,864Updated this week
- Ongoing research training transformer models at scale☆12,701Updated this week
- Code for the paper "Language Models are Unsupervised Multitask Learners"☆23,715Updated 10 months ago
- 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (i…☆8,875Updated this week
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆42,229Updated 6 months ago
- Tensors and Dynamic neural networks in Python with strong GPU acceleration☆91,018Updated this week
- TensorFlow code and pre-trained models for BERT☆39,262Updated 11 months ago
- Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.☆32,236Updated last week
- BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)☆7,491Updated 3 weeks ago
- AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file convert…☆21,281Updated this week
- 💥 Fast State-of-the-Art Tokenizers optimized for Research and Production☆9,836Updated this week
- Fast and memory-efficient exact attention☆18,043Updated this week
- Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.☆37,737Updated this week
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆18,861Updated this week
- An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.☆38,770Updated 3 weeks ago
- Code and documentation to train Stanford's Alpaca models, and generate the data.☆30,046Updated 11 months ago
- tiktoken is a fast BPE tokeniser for use with OpenAI's models.☆14,935Updated 3 months ago
- Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more☆32,619Updated this week
- Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.☆145,020Updated this week