microsoft / torchscale
Foundation Architecture for (M)LLMs
☆3,025Updated 6 months ago
Related projects ⓘ
Alternatives and complementary repositories for torchscale
- Accessible large language models via k-bit quantization for PyTorch.☆6,244Updated this week
- An open-source framework for training large multimodal models.☆3,732Updated 2 months ago
- Transformer related optimization, including BERT, GPT☆5,871Updated 7 months ago
- [ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters☆5,739Updated 7 months ago
- A concise but complete full-attention transformer with a set of promising experimental features from various papers☆4,760Updated this week
- 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…☆1,530Updated 8 months ago
- PyTorch extensions for high performance and large scale training.☆3,187Updated 2 months ago
- Fast and memory-efficient exact attention☆14,109Updated this week
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,500Updated 10 months ago
- ☆2,676Updated last week
- An implementation of "Retentive Network: A Successor to Transformer for Large Language Models"☆1,163Updated last year
- A Unified Library for Parameter-Efficient and Modular Transfer Learning☆2,566Updated last week
- 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (i…☆7,911Updated this week
- Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Ad…☆5,988Updated 2 months ago
- The hub for EleutherAI's work on interpretability and learning dynamics☆2,266Updated last week
- Cramming the training of a (BERT-type) language model into limited compute.☆1,294Updated 4 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…☆2,401Updated 2 months ago
- 🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch☆2,028Updated 4 months ago
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆1,922Updated 7 months ago
- maximal update parametrization (µP)☆1,396Updated 3 months ago
- General technology for enabling AI capabilities w/ LLMs and MLLMs☆3,680Updated last month
- A modular RL library to fine-tune language models to human preferences☆2,211Updated 8 months ago
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆8,612Updated this week
- The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”☆937Updated 9 months ago
- [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333☆1,041Updated 9 months ago
- Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised…☆2,813Updated 6 months ago
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆2,498Updated 3 weeks ago
- A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.☆2,303Updated last month
- TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.☆1,460Updated this week