microsoft / torchscale
Foundation Architecture for (M)LLMs
☆3,034Updated 7 months ago
Related projects ⓘ
Alternatives and complementary repositories for torchscale
- An implementation of "Retentive Network: A Successor to Transformer for Large Language Models"☆1,163Updated last year
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,502Updated 10 months ago
- 🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch☆2,041Updated 5 months ago
- Accessible large language models via k-bit quantization for PyTorch.☆6,299Updated this week
- PyTorch extensions for high performance and large scale training.☆3,195Updated last week
- 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (i…☆7,958Updated this week
- Transformer related optimization, including BERT, GPT☆5,890Updated 7 months ago
- A concise but complete full-attention transformer with a set of promising experimental features from various papers☆4,793Updated this week
- A modular RL library to fine-tune language models to human preferences☆2,213Updated 8 months ago
- [ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters☆5,760Updated 8 months ago
- Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackab…☆1,535Updated 9 months ago
- maximal update parametrization (µP)☆1,402Updated 4 months ago
- The hub for EleutherAI's work on interpretability and learning dynamics☆2,282Updated 2 weeks ago
- A Unified Library for Parameter-Efficient and Modular Transfer Learning☆2,581Updated 2 weeks ago
- General technology for enabling AI capabilities w/ LLMs and MLLMs☆3,699Updated last month
- Fast and memory-efficient exact attention☆14,279Updated this week
- A fast MoE impl for PyTorch☆1,565Updated 4 months ago
- An open-source framework for training large multimodal models.☆3,750Updated 2 months ago
- ☆2,686Updated this week
- Cramming the training of a (BERT-type) language model into limited compute.☆1,296Updated 5 months ago
- [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333☆1,045Updated 10 months ago
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆8,660Updated this week
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆1,338Updated 8 months ago
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆2,409Updated 3 months ago
- An Open-source Toolkit for LLM Development☆2,721Updated 5 months ago
- AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (N…☆4,561Updated 3 weeks ago
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆1,941Updated 7 months ago
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆1,893Updated last month
- TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.☆1,474Updated this week