huggingface / transformersLinks
π€ 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.
β146,154Updated 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. π Star to support our work!β38,779Updated this week
- DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.β39,142Updated this week
- Facebook AI Research Sequence-to-Sequence Toolkit written in Python.β31,582Updated 2 weeks ago
- Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.β29,665Updated this week
- Inference code for Llama modelsβ58,421Updated 5 months ago
- State-of-the-Art Text Embeddingsβ17,024Updated 2 weeks ago
- Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalitiesβ21,441Updated 3 weeks ago
- Unsupervised text tokenizer for Neural Network-based text generation.β11,022Updated 2 months ago
- A library for efficient similarity search and clustering of dense vectors.β35,725Updated this week
- π€ The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation toolsβ20,306Updated this week
- π¦π Build context-aware reasoning applicationsβ110,444Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMsβ50,864Updated this week
- Ongoing research training transformer models at scaleβ12,701Updated this week
- Code for the paper "Language Models are Unsupervised Multitask Learners"β23,715Updated 10 months ago
- π A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (iβ¦β8,875Updated this week
- The simplest, fastest repository for training/finetuning medium-sized GPTs.β42,229Updated 6 months ago
- Tensors and Dynamic neural networks in Python with strong GPU accelerationβ91,018Updated this week
- TensorFlow code and pre-trained models for BERTβ39,262Updated 11 months ago
- Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.β32,236Updated last week
- BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)β7,491Updated 3 weeks ago
- AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file convertβ¦β21,281Updated this week
- π₯ Fast State-of-the-Art Tokenizers optimized for Research and Productionβ9,836Updated this week
- Fast and memory-efficient exact attentionβ18,043Updated 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.β37,737Updated this week
- π€ PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.β18,861Updated this week
- An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.β38,770Updated 3 weeks ago
- Code and documentation to train Stanford's Alpaca models, and generate the data.β30,046Updated 11 months ago
- tiktoken is a fast BPE tokeniser for use with OpenAI's models.β14,935Updated 3 months ago
- Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and moreβ32,619Updated 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.β145,020Updated this week