Search Results for "settings" - Page 4
Sort By:
Showing 285 open source projects for "settings"
View related business solutions-
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.
-
$300 in Free Credit Towards Top Cloud ServicesStart your project in minutes. After credits run out, 20+ products include free monthly usage. Only pay when you're ready to scale.
-
1
PEFT
State-of-the-art Parameter-Efficient Fine-Tuning
Parameter-Efficient Fine-Tuning (PEFT) methods enable efficient adaptation of pre-trained language models (PLMs) to various downstream applications without fine-tuning all the model's parameters. Fine-tuning large-scale PLMs is often prohibitively costly. In this regard, PEFT methods only fine-tune a small number of (extra) model parameters, thereby greatly decreasing the computational and storage costs. Recent State-of-the-Art PEFT techniques achieve performance comparable to that of full... -
2
EasyR1
An Efficient, Scalable, Multi-Modality RL Training Framework
EasyR1 is a streamlined training framework for building “R1-style” reasoning models from open-source LLMs with minimal boilerplate. It focuses on the full reasoning stack—data preparation, supervised fine-tuning, preference or outcome-based optimization, and lightweight evaluation—so you can iterate quickly on chain-of-thought–heavy tasks. The project’s philosophy is practicality: sensible defaults, one-command recipes, and compatibility with popular base models let you stand up experiments... -
3
OneFileLLM
Specify a github or local repo, github pull request
...This design allows developers to share AI tools in a format that can be easily distributed and executed across different machines without complicated installation procedures. Such packaging strategies help make AI software easier to use in educational settings, demonstrations, and lightweight deployments. -
4
OpenTinker
OpenTinker is an RL-as-a-Service infrastructure for foundation models
...It introduces a centralized scheduler to manage distributed training jobs and shared compute resources, enabling workloads like reinforcement learning, supervised fine-tuning, and inference to run across multiple settings. The architecture supports a range of single-turn and multi-turn agentic tasks with a design that abstracts away infrastructure complexity while offering flexible Python APIs to define environments and workflows. -
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
5
SleepFM-Clinical
Improve human sleep through scientifically
...The clinical release includes additional features for controlled experimentation, such as logging capabilities, adjustable parameter sets, and protocols suitable for sleep studies and therapeutic settings. It also integrates tools for clinicians to configure sessions, annotate events, and potentially link with biofeedback data, enabling a more nuanced understanding of sound’s effect on sleep architecture over time. -
6
EPLB
Expert Parallelism Load Balancer
EPLB is DeepSeek’s open implementation of a load balancing algorithm designed for expert parallelism (EP) settings in MoE architectures. In EP, different “experts” are mapped to different GPUs or nodes, so load imbalance becomes a performance bottleneck if certain experts are invoked much more often. EPLB solves this by duplicating heavily used experts (redundancy) and then placing those duplicates across GPUs to even out computational load. -
7
Pyright
Static type checker for Python
...It can run in a “watch” mode and performs fast incremental updates when files are modified. Pyright supports configuration files that provide granular control over settings. Different “execution environments” can be associated with subdirectories within a source base. Each environment can specify different module search paths, python language versions, and platform targets. Type inference for function return values, instance variables, class variables, and globals. Type guards that understand conditional code flow constructs like if/else statements. ... -
8
Story Flicks
Generate high-definition story short videos with one click using AI
Story Flicks is another open-source project in the AI-assisted video generation / editing space, focused on creating short, story-style videos from script or prompt inputs. It aims to let users generate high-definition short movies or video stories with minimal manual effort, using AI models under the hood to assemble visuals, timing, and possibly narration or subtitles. For creators who want to produce narrative short-form content — whether for social media, storytelling, or prototyping... -
9
AutoViz
Automatically Visualize any dataset, any size
AutoViz is a Python data visualization library designed to automate exploratory data analysis by generating multiple visualizations with minimal code. The primary goal of the project is to help data scientists and analysts quickly understand patterns, relationships, and anomalies within datasets without manually writing complex plotting code. With a single command, the library can automatically generate dozens of charts and graphs that reveal insights into the structure and quality of the... -
Gemini 3 and 200+ AI Models on One PlatformBuild generative AI apps with Vertex AI. Switch between models without switching platforms.
-
10
Shell-AI
LangChain powered shell command generator and runner CLI
Shell-AI is an open-source command-line interface utility that allows users to generate and execute shell commands using natural language prompts. Instead of requiring users to remember complex command syntax, the tool lets them describe their intent in plain English and automatically suggests commands that accomplish the task. The system is powered by large language models and integrates with frameworks such as LangChain to interpret user requests and translate them into executable shell... -
11
TimesFM
Pretrained time-series foundation model developed by Google Research
TimesFM is a pretrained time-series foundation model from Google Research built for forecasting tasks, designed to generalize across many domains without requiring extensive per-dataset retraining. It provides a decoder-only model approach to forecasting, aiming for strong performance even in zero-shot or low-data settings where traditional models often struggle. The project includes code and an inference API intended to make it practical to run forecasts programmatically, with options to use different backends such as Torch or Flax depending on your environment and performance needs. Newer releases emphasize expanded context handling and more flexible forecasting outputs, including quantile forecasting so users can get uncertainty estimates rather than only point predictions. ... -
12
PAL MCP
The power of Claude Code / GeminiCLI / CodexCLI
PAL MCP is an open-source Model Context Protocol (MCP) server designed to act as a powerful middleware layer that connects AI clients and tools—like Claude Code, Codex CLI, Cursor, and IDE plugins—to a broad range of underlying AI models, enabling collaborative multi-model workflows rather than relying on a single model. It lets developers orchestrate interactions across multiple models (including Gemini, OpenAI, Grok, Azure, Ollama, OpenRouter, and custom/self-hosted models), preserving... -
13
Context Engineering Template
Context engineering is the new vibe coding
...The repository provides templates such as CLAUDE.md for defining global project rules, INITIAL.md for feature requests, and folders for examples, PRPs, validation scripts, and settings to support systematic prompt generation and execution with tools like Claude Code. By using this template, teams can ensure consistency across AI outputs, reduce errors that stem from contextual misunderstandings, and build reusable patterns. -
14
WorldGen
Generate Any 3D Scene in Seconds
...The core idea is that you describe a world in natural language and WorldGen produces a navigable 3D scene that you can freely explore in 360 degrees, with loop closure so that the space remains consistent as you move around. It supports a wide variety of scenes, including both indoor and outdoor settings, and can handle realistic as well as stylized or fantastical environments. Rendering is decoupled from generation, so you can render at arbitrary resolutions and camera trajectories in real time, which makes it easier to integrate into custom pipelines. -
15
Granite TSFM
Foundation Models for Time Series
...The ecosystem around TSFM also includes a community cookbook of “recipes” that showcase capabilities and patterns. Overall, the repo is designed as a hands-on companion for teams adopting time-series foundation models in production-leaning settings. -
16
MetaCLIP
ICLR2024 Spotlight: curation/training code, metadata, distribution
...It includes utilities to fine-tune vision-language embeddings, compute prompt or adapter updates, and benchmark across transfer and retention metrics. MetaCLIP is especially suited for real-world settings where a model must continuously incorporate new visual categories or domains over time. -
17
Pearl
A Production-ready Reinforcement Learning AI Agent Library
Pearl is a production-ready reinforcement learning and contextual bandit agent library built for real-world sequential decision making. It is organized around modular components—policy learners, replay buffers, exploration strategies, safety modules, and history summarizers—that snap together to form reliable agents with clear boundaries and strong defaults. The library implements classic and modern algorithms across two regimes: contextual bandits (e.g., LinUCB, LinTS, SquareCB, neural... -
18
Flow Matching
A PyTorch library for implementing flow matching algorithms
flow_matching is a PyTorch library implementing flow matching algorithms in both continuous and discrete settings, enabling generative modeling via matching vector fields rather than diffusion. The underlying idea is to parameterize a flow (a time-dependent vector field) that transports samples from a simple base distribution to a target distribution, and train via matching of flows without requiring score estimation or noisy corruption—this can lead to more efficient or stable generative training. ... -
19
Smallpond
A lightweight data processing framework built on DuckDB and 3FS
smallpond is a lightweight distributed data processing framework built by DeepSeek, designed to scale DuckDB workloads over clusters using their 3FS (Fire-Flyer File System) backend. The idea is to preserve DuckDB’s fast analytics engine but lift it from single-node to multi-node settings, giving you the ability to operate on large datasets (e.g. petabyte scale) without moving to a heavyweight system like Spark. Users write Python-like code (via DataFrame APIs or SQL strings) to express their transformations; behind the scenes, tasks are scheduled (often via Ray) and pushed into DuckDB instances operating on partitioned data. ... -
20
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.... -
21
JobFunnel
Scrape job websites into a single spreadsheet with no duplicates.
...You can search for jobs with YAML configuration files or by passing command arguments. By performing regular scraping and reviewing, you can cut through the noise of even the busiest job markets. Run funnel with your settings YAML to populate your master CSV file with jobs from available providers. JobFunnel can be easily automated to run nightly with crontab. If you have a job website you'd like to write a scraper for, you are welcome to implement it, Review the Base Scraper for implementation details. JobFunnel supports scraping jobs from the same job website across locales & domains. ... -
22
Mail-in-a-Box
Take back control of your email with this mail server in a box
Mail-in-a-Box helps individuals take back control of their email by defining a one-click, easy-to-deploy SMTP+everything else server, a mail server in a box. Mail-in-a-Box lets you become your own mail service provider in a few easy steps. It’s sort of like making your own gmail, but one you control from top to bottom. Technically, Mail-in-a-Box turns a fresh cloud computer into a working mail server. But you don’t need to be a technology expert to set it up. Our goals are to make deploying... -
23
rLLM
Democratizing Reinforcement Learning for LLMs
...The project is designed to support large-scale language models (including support for big models via integrated training backends), making it relevant for state-of-the-art research and production use. The framework includes tools for defining workflows, specifying objectives or reward functions, and managing training/policy updates across possibly distributed settings. -
24
Stable Diffusion WebUI Forge
Stable Diffusion WebUI Forge is a platform on top of Stable Diffusion
Stable Diffusion WebUI Forge is a performance- and feature-oriented fork of the popular AUTOMATIC1111 interface that experiments with new backends, memory optimizations, and UX improvements. It targets heavy users and researchers who push large models, control nets, and high-resolution pipelines where default settings can become bottlenecks. The fork typically introduces toggles for scheduler behavior, attention implementations, caching, and precision modes to reach better speed or quality on given hardware. It also focuses on stability during long sessions, aiming to reduce out-of-memory failures and provide clearer diagnostics when they occur. ... -
25
Janus
Unified Multimodal Understanding and Generation Models
Janus is a sophisticated open-source project from DeepSeek AI that aims to unify both visual understanding and image generation in a single model architecture. Rather than having separate systems for “look and describe” and “prompt and generate”, Janus uses an autoregressive transformer framework with a decoupled visual encoder—allowing it to ingest images for comprehension and to produce images from text prompts with shared internal representations. The design tackles long-standing...
