Search Results for "blocks"
Sort By:
Showing 53 open source projects for "blocks"
View related business solutions-
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
1
HunyuanVideo-Foley
Multimodal Diffusion with Representation Alignment
...The model architecture aligns audio, video, and text representations to produce realistic synchronized soundtracks. Produces high-quality 48 kHz audio output suitable for professional use. Hybrid architecture combining multimodal transformer blocks and unimodal refinement blocks. Temporal alignment via frame-level synchronization modules (e.g. Synchformer). -
2
xFormers
Hackable and optimized Transformers building blocks
...The library includes memory-efficient operator implementations in both Python and optimized C++/CUDA, ensuring that performance isn’t sacrificed for modularity. It also integrates with PyTorch seamlessly so you can drop in its blocks to existing models, replace default attention layers, or build new architectures from scratch. xformers includes training, deployment, and memory profiling tools. -
3
LangCheck
Simple, Pythonic building blocks to evaluate LLM applications
Simple, Pythonic building blocks to evaluate LLM applications. -
4
Diffusers
State-of-the-art diffusion models for image and audio generation
...State-of-the-art diffusion pipelines that can be run in inference with just a few lines of code. Interchangeable noise schedulers for different diffusion speeds and output quality. Pretrained models that can be used as building blocks, and combined with schedulers, for creating your own end-to-end diffusion systems. We recommend installing Diffusers in a virtual environment from PyPi or Conda. For more details about installing PyTorch and Flax, please refer to their official documentation. -
Error to trace to log to deploy. One click. No SSH.AppSignal links every error to the trace, the trace to the log, the log to the deploy that shipped it.
-
5
ModernBERT
Bringing BERT into modernity via both architecture changes and scaling
...ModernBERT introduces architectural improvements that enhance both training efficiency and inference performance, making the model more suitable for modern large-scale machine learning pipelines. The repository also includes FlexBERT, a modular framework that allows developers to experiment with different encoder building blocks and configurations when constructing new models. -
6
Optax
Optax is a gradient processing and optimization library for JAX
Optax is a gradient processing and optimization library for JAX. It is designed to facilitate research by providing building blocks that can be recombined in custom ways in order to optimize parametric models such as, but not limited to, deep neural networks. We favor focusing on small composable building blocks that can be effectively combined into custom solutions. Others may build upon these basic components in more complicated abstractions. Whenever reasonable, implementations prioritize readability and structuring code to match standard equations, over code reuse. -
7
LLMs-from-scratch
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
LLMs-from-scratch is an educational codebase that walks through implementing modern large-language-model components step by step. It emphasizes building blocks—tokenization, embeddings, attention, feed-forward layers, normalization, and training loops—so learners understand not just how to use a model but how it works internally. The repository favors clear Python and NumPy or PyTorch implementations that can be run and modified without heavyweight frameworks obscuring the logic. Chapters and notebooks progress from tiny toy models to more capable transformer stacks, including sampling strategies and evaluation hooks. ... -
8
Vision Transformer Pytorch
Implementation of Vision Transformer, a simple way to achieve SOTA
This repository provides a from-scratch, minimalist implementation of the Vision Transformer (ViT) in PyTorch, focusing on the core architectural pieces needed for image classification. It breaks down the model into patch embedding, positional encoding, multi-head self-attention, feed-forward blocks, and a classification head so you can understand each component in isolation. The code is intentionally compact and modular, which makes it easy to tinker with hyperparameters, depth, width, and attention dimensions. Because it stays close to vanilla PyTorch, you can integrate custom datasets and training loops without framework lock-in. ... -
9
AutoGPT
Powerful tool that lets you create and run intelligent agents
AutoGPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. This program, driven by GPT-4, chains together LLM "thoughts", to autonomously achieve whatever goal you set. As one of the first examples of GPT-4 running fully autonomously, AutoGPT pushes the boundaries of what is possible with AI. -
Secure File Transfer for Windows with Cerberus by RedwoodCerberus supports unlimited users and connections on a single IP, with built-in encryption, 2FA, and a browser-based web client — all deployable in under 15 minutes with a 25-day free trial.
-
10
Llama Stack
Composable building blocks to build Llama Apps
Llama-Stack is an open-source framework designed to facilitate the deployment and fine-tuning of large language models (LLMs) for various natural language processing tasks. -
11
files-to-prompt
Concatenate a directory full of files into a single prompt
...It includes rich filtering controls, letting you limit by extension, include or skip hidden files, and ignore paths that match glob patterns or .gitignore rules. The output format is flexible: you can emit plain text, Markdown with fenced code blocks, or a Claude-XML style format designed for structured multi-file prompts. It can read file paths from stdin (including NUL-separated paths), which makes it easy to combine with find, rg, or other shell tools. -
12
Ludwig AI
Low-code framework for building custom LLMs, neural networks
...Support for hyperparameter optimization, explainability, and rich metric visualizations. Experiment with different model architectures, tasks, features, and modalities with just a few parameter changes in the config. Think building blocks for deep learning. -
13
Claude Code SDK Python
Python SDK for Claude Agent
...The repo is MIT-licensed and includes documentation and installation instructions (requires Python 3.10+, Node installation of Claude Code). Example usage shows how to stream responses, parse structured message blocks, or create persistent client sessions. -
14
Burr
Build applications that make decisions. Chatbots, agents, simulations
Burr makes it easy to develop applications that make decisions (chatbots, agents, simulations, etc...) from simple python building blocks. Burr works well for any application that uses LLMs and can integrate with any of your favorite frameworks. Burr includes a UI that can track/monitor/trace your system in real-time, along with pluggable persisters (e.g. for memory) to save & load application state. -
15
Transformer Engine
A library for accelerating Transformer models on NVIDIA GPUs
Transformer Engine (TE) is a library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper GPUs, to provide better performance with lower memory utilization in both training and inference. TE provides a collection of highly optimized building blocks for popular Transformer architectures and an automatic mixed precision-like API that can be used seamlessly with your framework-specific code. TE also includes a framework-agnostic C++ API that can be integrated with other deep-learning libraries to enable FP8 support for Transformers. As the number of parameters in Transformer models continues to grow, training and inference for architectures such as BERT, GPT, and T5 become very memory and compute-intensive. ... -
16
agentic-stack
One brain, many harnesses. Portable .agent/ folder
...It may include abstractions for memory, planning, and tool usage, reflecting modern agentic AI design patterns. The stack is intended to accelerate development by providing reusable building blocks for complex AI systems. Overall, it represents an infrastructure layer for creating autonomous or semi-autonomous AI applications. -
17
Adapters
A Unified Library for Parameter-Efficient Learning
...Adapters provide a unified interface for efficient fine-tuning and modular transfer learning, supporting a myriad of features like full-precision or quantized training (e.g. Q-LoRA, Q-Bottleneck Adapters, or Q-PrefixTuning), adapter merging via task arithmetics or the composition of multiple adapters via composition blocks, allowing advanced research in parameter-efficient transfer learning for NLP tasks. -
18
Learn Claude Code
Bash is all you need, write a claude code with only 16 line code
Learn Claude Code is an educational repository that teaches how modern AI coding agents work by walking learners through a sequence of progressively more complex agent implementations, starting with a minimal Bash-based agent and culminating in agents with explicit planning, subagents, and skills. It emphasizes a hands-on learning path where each version (from v0 to v4) adds conceptual building blocks like the core agent loop, todo planning, task decomposition, and domain knowledge skills, illuminating the patterns behind what makes a true AI agent tick. The goal is to demystify agent architectures like Claude Code by having learners build simplified versions themselves and observe how tools, memory management, planning constraints, and context isolation contribute to reliable agent behavior. ... -
19
Gemma in PyTorch
The official PyTorch implementation of Google's Gemma models
...Example notebooks walk through instruction tuning and evaluation so teams can benchmark and iterate rapidly. The code is organized to be legible and hackable, exposing attention blocks, positional encodings, and head configurations. With standard PyTorch abstractions, it integrates easily into existing training loops, loggers, and evaluation harnesses. -
20
FiftyOne
The open-source tool for building high-quality datasets
...Improving data quality and understanding your model’s failure modes are the most impactful ways to boost the performance of your model. FiftyOne provides the building blocks for optimizing your dataset analysis pipeline. Use it to get hands-on with your data, including visualizing complex labels, evaluating your models, exploring scenarios of interest, identifying failure modes, finding annotation mistakes, and much more! Surveys show that machine learning engineers spend over half of their time wrangling data, but it doesn't have to be that way. -
21
Toad
Unified terminal AI tool for exploring and editing codebases
Toad is an open source, terminal-first AI interface designed to unify multiple coding agents into a single workflow. It allows developers to interact with AI models directly inside the command line, making it easier to explore, understand, and modify codebases without leaving the terminal. Built in Python, it focuses on transparency and control by letting users load context intentionally and inspect how the AI processes files. Toad supports structured conversations, enabling navigation... -
22
AstronRPA
Agent-ready RPA suite with visual workflow automation tools engine
...Astron RPA includes a large library of reusable components that handle tasks such as user interface operations, data processing, and system interactions, allowing workflows to be assembled from modular building blocks. Astron RPA also integrates with intelligent agent systems so that automated processes and AI-driven workflows can work together in broader automation scenarios. -
23
MoBA
MoBA: Mixture of Block Attention for Long-Context LLMs
...The architecture adapts ideas from Mixture-of-Experts networks and applies them directly to the attention mechanism of transformer models. Instead of forcing each token to attend to every other token in the sequence, MoBA divides the context into blocks and dynamically routes queries to only the most relevant segments of information. This routing strategy reduces the computational cost associated with traditional attention while preserving performance on reasoning and long-context tasks. The approach allows language models to scale to significantly longer input contexts without the quadratic computational cost normally associated with transformer attention mechanisms. -
24
TimeMixer
Decomposable Multiscale Mixing for Time Series Forecasting
...Instead of relying on traditional recurrent or transformer-based architectures, TimeMixer is implemented as a fully multilayer perceptron–based model that performs temporal mixing across different resolutions of the data. The architecture introduces specialized components such as Past-Decomposable-Mixing blocks, which extract information from historical sequences at different scales, and Future-Multipredictor-Mixing modules that combine predictions from multiple forecasting paths. This design allows the model to integrate complementary information across scales and produce more accurate predictions for complex temporal patterns. -
25
xLSTM
Neural Network architecture based on ideas of the original LSTM
xLSTM is an open-source machine learning architecture that reimagines the classic Long Short-Term Memory (LSTM) network for modern large-scale language modeling and sequence processing tasks. The project introduces a new recurrent neural network design that incorporates exponential gating mechanisms and enhanced memory structures to overcome limitations of traditional LSTM models. By introducing innovations such as matrix-based memory and improved normalization techniques, xLSTM improves the...
