facebookresearch / xformers
Hackable and optimized Transformers building blocks, supporting a composable construction.
β9,435Updated last week
Alternatives and similar repositories for xformers:
Users that are interested in xformers are comparing it to the libraries listed below
- Fast and memory-efficient exact attentionβ17,192Updated this week
- Accessible large language models via k-bit quantization for PyTorch.β6,972Updated this week
- π A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (iβ¦β8,673Updated this week
- An open source implementation of CLIP.β11,654Updated last week
- π€ Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.β28,835Updated this week
- Transformer related optimization, including BERT, GPTβ6,144Updated last year
- Using Low-rank adaptation to quickly fine-tune diffusion models.β7,328Updated last year
- LAVIS - A One-stop Library for Language-Vision Intelligenceβ10,516Updated 5 months ago
- Simple, safe way to store and distribute tensorsβ3,249Updated last month
- Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"β7,224Updated 11 months ago
- AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (Nβ¦β4,630Updated last month
- Ongoing research training transformer models at scaleβ12,261Updated this week
- π€ PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.β18,274Updated this week
- [ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parametersβ5,868Updated last year
- Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"β11,847Updated 4 months ago
- A concise but complete full-attention transformer with a set of promising experimental features from various papersβ5,288Updated last week
- High-Resolution Image Synthesis with Latent Diffusion Modelsβ12,767Updated last year
- RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable)β¦β13,564Updated this week
- PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationβ5,212Updated 9 months ago
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.β4,826Updated 3 weeks ago
- Development repository for the Triton language and compilerβ15,447Updated this week
- Foundation Architecture for (M)LLMsβ3,074Updated last year
- An open-source framework for training large multimodal models.β3,904Updated 8 months ago
- QLoRA: Efficient Finetuning of Quantized LLMsβ10,411Updated 10 months ago
- Train transformer language models with reinforcement learning.β13,559Updated this week
- Karras et al. (2022) diffusion models for PyTorchβ2,449Updated 3 months ago
- π Accelerate inference and training of π€ Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimizationβ¦β2,873Updated this week
- PyTorch extensions for high performance and large scale training.β3,308Updated last week
- β2,800Updated this week
- Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.β4,016Updated 8 months ago