Search Results for "activation"
Sort By:
Showing 166 open source projects for "activation"
View related business solutions-
Earn up to 16% annual interest with Nexo.Generate interest, borrow against your crypto, and trade a range of cryptocurrencies — all in one platform. Geographic restrictions, eligibility, and terms apply.
-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
1
Open Aimbot
Universal Aim Assist Framework
Open Aimbot is an open-source aim assist framework created for Roblox and designed to provide a wide range of targeting and player-tracking features. The project offers a highly customizable interface that allows users to adjust targeting behavior, visual overlays, and activation settings. Built as a universal framework, it supports multiple exploit environments and device configurations. Open Aimbot includes numerous filtering options that can differentiate targets based on factors such as teams, friends, player status, and visibility conditions. The framework also features configuration management tools, enabling users to save and switch between custom setups. ... -
2
go-systemd
Go bindings to systemd socket activation, journal, D-Bus
Go bindings to systemd socket activation, journal, D-Bus, and unit files. Activation, for writing and using socket activation from Go. Daemon, for notifying systemd of service status changes. Dbus, for starting/stopping/inspecting running services and units. Journal, for writing to systemd's logging service, journals. Sdjournal, for reading from journald by wrapping its C API. -
3
Transformer Debugger
Tool for exploring and debugging transformer model behaviors
...TDB allows users to intervene directly in the forward pass of a model and observe how such interventions change predictions, making it possible to answer questions like why a token was selected or why an attention head focused on a certain input. It automatically identifies and explains the most influential components, highlights activation patterns, and maps relationships across circuits within the model. The tool includes both a React-based neuron viewer for exploring model components and a backend activation server for running inferences and serving data. -
4
TuyaOpen
Next-gen AI+IoT framework for T2/T3/T5AI/ESP32/and more
...The system includes built-in networking support for communication protocols such as Wi-Fi, Bluetooth, and Ethernet, allowing devices to connect securely to remote services and applications. TuyaOpen also integrates with Tuya’s broader cloud ecosystem, enabling developers to manage device authentication, firmware updates, device activation, and remote monitoring from centralized services. -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
5
Flox
Developer environments you can take with you
...The ecosystem includes CI building blocks—for example, a CircleCI Orb—to install and activate environments as part of builds and tests. Flox’s messaging focuses on faster onboarding and “time-to-activation,” reducing friction for new contributors and multi-repo organizations. In practice, it functions as both the package source and the environment switcher, keeping toolchains isolated and reproducible. -
6
Ring
Ring is a reasoning MoE LLM provided and open-sourced by InclusionAI
Ring is a reasoning Mixture-of-Experts (MoE) large language model (LLM) developed by inclusionAI. It is built from or derived from Ling. Its design emphasizes reasoning, efficiency, and modular expert activation. In its “flash” variant (Ring-flash-2.0), it optimizes inference by activating only a subset of experts. It applies reinforcement learning/reasoning optimization techniques. Its architectures and training approaches are tuned to enable efficient and capable reasoning performance. Reasoning-optimized model with reinforcement learning enhancements. ... -
7
PowerInfer
High-speed Large Language Model Serving for Local Deployment
...This hybrid execution strategy significantly reduces memory bottlenecks and improves overall inference speed. PowerInfer incorporates specialized algorithms and sparse operators to manage neuron activation patterns and minimize data transfers between hardware components. As a result, it enables powerful language models to run on consumer hardware while achieving performance comparable to more expensive server-grade systems. -
8
MobileLLM
MobileLLM Optimizing Sub-billion Parameter Language Models
...Introduced in the ICML 2024 paper “MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases”, it focuses on delivering strong reasoning and generalization capabilities in models under one billion parameters. The framework integrates several architectural innovations—SwiGLU activation, deep and thin network design, embedding sharing, and grouped-query attention (GQA)—to achieve a superior trade-off between model size, inference speed, and accuracy. MobileLLM demonstrates remarkable performance, with the 125M and 350M variants outperforming previous state-of-the-art models of the same scale by up to 4.3% on zero-shot commonsense reasoning tasks. -
9
NextChat
Light and Fast AI Assistant
NextChat is a browser extension that injects a floating ChatGPT-style chat sidebar into webpages, enabling instant AI assistance during web browsing. It supports context-aware chatting using page content, quick queries, and code assistance without opening a new tab. Developers appreciate its customization options—like hotkeys, themes, and engine selection—while everyday users enjoy handy tools for writing, summarizing, or brainstorming on the fly. -
One Monitoring Tool for IT, OT and Cloud | Free TrialModern infrastructure spans data centers, cloud platforms and factory floors, and every blind spot between them is a risk. PRTG supports SNMP, WMI, SSH and other standard protocols to monitor IT, OT and hybrid environments through one customizable dashboard. Build the views your team needs, from network health to application performance, without switching tools. Try PRTG free for 30 days now.
-
10
Claude Cognitive
Persistent context and multi-instance coordination
...It introduces an attention-based context router that prioritizes files and content relevant to the current development discussion — tagging them as HOT, WARM, or COLD based on recency and keyword activation — so Claude Code doesn’t waste token budget rereading irrelevant code. This context routing dramatically reduces redundant token usage and accelerates large codebase interactions by focusing only on what truly matters to the current task. Additionally, Claude-Cognitive includes a pool coordinator to share state across multiple Claude Code instances, preserving what’s been learned or completed and preventing repetitive debugging or redundant exploration. -
11
Ling
Ling is a MoE LLM provided and open-sourced by InclusionAI
Ling is a Mixture-of-Experts (MoE) large language model (LLM) provided and open-sourced by inclusionAI. The project offers different sizes (Ling-lite, Ling-plus) and emphasizes flexibility and efficiency: being able to scale, adapt expert activation, and perform across a range of natural language/reasoning tasks. Example scripts, inference pipelines, and documentation. The codebase includes inference, examples, models, documentation, and model download infrastructure. As more developers and researchers engage with the platform, we can expect rapid advancements and improvements, leading to even more sophisticated applications. ... -
12
Magisk on WSA
Integrate Magisk root and Google Apps into WSA
...The repository includes scripts that streamline setup across Linux distributions like Ubuntu, Debian, Arch, and openSUSE, supporting both ARM64 and x64 architectures. It offers features such as unattended installation, automatic developer mode activation, and seamless updates without data loss. This project has become popular among advanced users who want more control over Android on Windows. Note: support for Magisk on WSA will end after March 5, 2025. -
13
OpenWhip
Optimize interaction with AI coding assistants
OpenWhip is a desktop utility built as a cross-platform Node.js application that humorously gamifies interaction with AI coding assistants by simulating a “whip” tool to interrupt and motivate them during long or stalled operations. The application runs as a lightweight system tray program and overlays a visual whip animation on the screen when activated, creating an interactive and slightly absurd interface for user engagement. Its core functionality is surprisingly practical beneath the... -
14
XNNPACK
High-efficiency floating-point neural network inference operators
XNNPACK is a highly optimized, low-level neural network inference library developed by Google for accelerating deep learning workloads across a variety of hardware architectures, including ARM, x86, WebAssembly, and RISC-V. Rather than serving as a standalone ML framework, XNNPACK provides high-performance computational primitives—such as convolutions, pooling, activation functions, and arithmetic operations—that are integrated into higher-level frameworks like TensorFlow Lite, PyTorch Mobile, ONNX Runtime, TensorFlow.js, and MediaPipe. The library is written in C/C++ and designed for maximum portability, efficiency, and performance, leveraging platform-specific instruction sets (e.g., NEON, AVX, SIMD) for optimized execution. ... -
15
fvcore
Collection of common code shared among different research projects
...Its common modules include timers, logging, checkpoints, registry patterns, and configuration helpers that reduce boilerplate in research code. A standout capability is FLOP and activation counting, which analyzes arbitrary PyTorch graphs to report cost by operator and by module for precise profiling. The file I/O layer (PathManager) abstracts local/remote storage so the same code can read from disks, cloud buckets, or HTTP endpoints. Because it is small, stable, and well-tested, fvcore is frequently imported by projects like Detectron2 and PyTorchVideo to avoid duplicating infrastructure and to keep research repos. -
16
SetupMiniconda
Set up your GitHub Actions workflow with conda via miniconda
setup-miniconda is a GitHub Action that sets up a Miniconda environment in CI/CD workflows. It simplifies the process of installing and configuring conda environments, enabling developers to manage dependencies and environments efficiently within their automated pipelines. -
17
Misago
Misago is fully featured modern forum application
...Your users may register accounts, set avatars, change options and edit their profiles. They have the option to reset forgotten passwords. Site admins may require users to confirm validity of their e-mail addresses via e-mail sent activation link, or limit user account activation to administrator action. They can use custom Q&A challenge, ReCAPTCHA, Stop Forum Spam or IP's blacklist to combat spam registrations. Pletora of settings are available to control user account behavior, like username lengths or avatar restrictions. Presence features let site members know when other users are online, offline or banned. ... -
18
pycm
Multi-class confusion matrix library in Python
PyCM is a multi-class confusion matrix library written in Python that supports both input data vectors and direct matrix, and a proper tool for post-classification model evaluation that supports most classes and overall statistics parameters. PyCM is the swiss-army knife of confusion matrices, targeted mainly at data scientists that need a broad array of metrics for predictive models and an accurate evaluation of large variety of classifiers. -
19
Kimi K2
Kimi K2 is the large language model series developed by Moonshot AI
Kimi K2 is Moonshot AI’s advanced open-source large language model built on a scalable Mixture-of-Experts (MoE) architecture that combines a trillion total parameters with a subset of ~32 billion active parameters to deliver powerful and efficient performance on diverse tasks. It was trained on an enormous corpus of over 15.5 trillion tokens to push frontier capabilities in coding, reasoning, and general agentic tasks while addressing training stability through novel optimizer and... -
20
NextDNS
NextDNS CLI client (DoH Proxy)
NextDNS protects you from all kinds of security threats, blocks ads and trackers on websites and in apps and provides a safe and supervised Internet for kids, on all devices and on all networks. Determine your threat model and fine-tune your security strategy by enabling 10+ different types of protections. Use the most trusted threat intelligence feeds containing millions of malicious domains, all updated in real-time. Go beyond the domain, we analyze DNS questions and answers on-the-fly (in... -
21
FlashKDA
High-performance Kimi Delta Attention kernels
...The package integrates with flash-linear-attention and can be selected automatically as the backend for chunk_kda during inference. It supports recurrent state input and output, variable-length batches, internal gating, query-key normalization, and beta activation. Builds can target the detected GPU architecture or multiple supported architectures for wheels and CI pipelines. The repository also provides correctness tests, benchmark material, a direct Python kernel API, and development helpers for CUDA and C++ tooling. -
22
jlens
Companion code for the global workspace interpretability paper
Jacobian Lens is Anthropic’s reference implementation for examining what a language model’s internal activations are inclined to produce as text. It transports residual-stream vectors from selected layers and positions into the final-layer basis using an averaged input-output Jacobian. The transformed vectors are decoded through the model’s own unembedding into ranked vocabulary predictions. The package can fit new lenses, load saved ones, apply them to prompts, and merge results from... -
23
Isso
a Disqus alternative
...It aims to be a drop-in replacement for Disqus. Users can edit or delete own comments (within 15 minutes by default). Comments in moderation queue are not publicly visible before activation. You can migrate your Disqus/WordPress comments without any hassle. Embed a single JS file, 40kb (12kb gzipped) and you are done. It allows anonymous comments, maintains identity and is simple to administrate. It uses JavaScript and cross-origin resource sharing for easy integration into (static) websites. No anonymous comments (IP address, email and name recorded), hosted in the USA, third-party. ... -
24
BigMac
An open-source toolkit for BigMac-style pipeline-parallel training
BigMac is an open-source toolkit for pipeline-parallel training of multimodal large language models. It preserves optimized language-model pipeline schedules while placing encoder and generator work around them. This design reduces activation memory without bringing back cross-module pipeline bubbles. Its scheduler creates global operator plans, while its executor runs those plans through a shared schedule abstraction. A Megatron-Core reference backend and Qwen3 and Qwen3-VL tutorials help developers connect the approach to real training workflows. The simulator lets researchers visualize schedules, compare pipeline strategies, and model timing imbalances caused by compute cost, input size, or uneven stage partitioning. ... -
25
TorchCode
Practice implementing softmax, attention, GPT-2 and more
...It is structured similarly to competitive programming platforms like LeetCode but focuses specifically on tensor operations and deep learning concepts. The platform provides a collection of curated problems that cover fundamental topics such as activation functions, normalization layers, attention mechanisms, and full transformer architectures. It runs in a Jupyter-based environment, allowing users to write, test, and debug their code interactively while receiving immediate feedback. An automated judging system evaluates correctness, gradient flow, and numerical stability, helping users understand both functional and theoretical aspects of their implementations.
