Search Results for "model-builder" - Page 35
Sort By:
Showing 2224 open source projects for "model-builder"
View related business solutions-
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
Earn up to 16% annual interest with Nexo.Put idle assets to work with competitive interest rates, borrow without selling, and trade with precision. All in one platform. Geographic restrictions, eligibility, and terms apply.
-
1
The LLM Evaluation guidebook
Sharing both practical insights and theoretical knowledge about LLM
...It compiles practical insights and theoretical knowledge gathered from real-world evaluation work, including experience managing the Open LLM Leaderboard and designing evaluation tools. The guidebook teaches developers how to design evaluation pipelines, select appropriate metrics, and interpret model performance results. It discusses multiple evaluation strategies, ranging from automated benchmarks to human evaluation and LLM-based evaluation techniques. The material also highlights the strengths and weaknesses of different evaluation methods, helping practitioners understand when and how to apply them. By organizing evaluation knowledge into structured sections, the project helps engineers and researchers build more reliable and trustworthy AI systems. -
2
MatMul-Free LM
Implementation for MatMul-free LM
MatMul-Free LM is an experimental implementation of a large language model architecture designed to eliminate traditional matrix multiplication operations used in transformer networks. Since matrix multiplication is one of the most computationally expensive components of modern language models, the project explores alternative computational strategies that reduce hardware requirements while maintaining comparable performance. -
3
Torch Pruning
DepGraph: Towards Any Structural Pruning
...Torch-Pruning physically removes parameters rather than masking them, which results in smaller and faster models during both training and inference. The toolkit supports a wide variety of architectures used in computer vision and large language models, making it a flexible solution for model compression tasks. -
4
LLM Workflow Engine
Power CLI and Workflow manager for LLMs (core package)
...The platform allows users to interact with AI models directly from the terminal, enabling conversational AI access through shell commands and scripts. Instead of focusing solely on chat interactions, the system is built to embed LLM calls into larger automation pipelines where model outputs can drive decision making or trigger additional processes. Developers can construct structured workflows using configuration files and integrate them with tools such as Ansible playbooks or custom scripts to automate complex tasks. The engine supports multiple AI providers through a plugin architecture, allowing connections to services like OpenAI, Hugging Face, Cohere, or other compatible APIs. -
Stop Cyber Threats with VM-Series Next-Gen Firewall on AzureGain integrated visibility across all traffic in a single pass. Deploy Palo Alto Networks VM-Series to determine application identity and content while automating security policy updates via rich APIs.
-
5
llms-from-scratch-cn
Build a large language model from 0 only with Python foundation
llms-from-scratch-cn is an educational open-source project designed to teach developers how to build large language models step by step using practical code and conceptual explanations. The repository provides a hands-on learning path that begins with the fundamentals of natural language processing and gradually progresses toward implementing full GPT-style architectures from the ground up. Rather than focusing on using pre-trained models through APIs, the project emphasizes understanding... -
6
The Alignment Handbook
Robust recipes to align language models with human and AI preferences
The Alignment Handbook is an open-source resource created to provide practical guidance for aligning large language models with human preferences and safety requirements. The project focuses on the post-training stage of model development, where models are refined after pre-training to behave more helpfully, safely, and reliably in real-world applications. It provides detailed training recipes that explain how to perform tasks such as supervised fine-tuning, preference modeling, and reinforcement learning from human feedback. The handbook also includes reproducible workflows for training instruction-following models and evaluating alignment quality across different datasets and benchmarks. ... -
7
Token-Oriented Object Notation
Token-Oriented Object Notation (TOON)
...The format aims to reduce token overhead compared with traditional formats like JSON while remaining human-readable and structurally expressive. TOON represents the same data model as JSON but removes unnecessary syntax such as braces and quotes, relying instead on indentation and structured tokens to represent objects and arrays. This design allows prompts containing structured data to use significantly fewer tokens, which can reduce inference costs and improve efficiency in LLM applications. The project includes a formal specification, encoding rules, and reference implementations that developers can use to serialize and parse TOON data in their applications. -
8
slime LLM
slime is an LLM post-training framework for RL Scaling
slime is an open-source large language model (LLM) post-training framework developed to support reinforcement learning (RL)-based scaling and high-performance training workflows for advanced LLMs, blending training and rollout modules into an extensible system. It offers a flexible architecture that connects high-throughput training (e.g., via Megatron-LM) with a customizable data generation pipeline, enabling researchers and engineers to iterate on new RL training paradigms effectively. ... -
9
Agent Reinforcement Trainer
Train multi-step agents for real-world tasks using GRPO
Agent Reinforcement Trainer, or ART is an open-source reinforcement learning framework tailored to training large language model agents through experience, making them more reliable and performant on multi-turn, multi-step tasks. Instead of just manually crafting prompts or relying on supervised fine-tuning, ART uses techniques like Group Relative Policy Optimization (GRPO) to let agents learn from environmental feedback and reward signals. The framework is designed to integrate easily with Python applications, abstracting much of the RL infrastructure so developers can train agents without deep RL expertise or heavy infrastructure overhead. ... -
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.
-
10
CoAI.Dev
Next Generation AI One-Stop Internationalization Solution
CoAI.Dev is an open-source “one-stop” AIGC web application that combines a modern chat-first UI with a full backend for running, managing, and monetizing multiple AI model providers from one place. It is designed to support a wide range of LLM and image-generation backends (including OpenAI-compatible endpoints), while also providing an admin dashboard for user, subscription, and pricing controls, so it can be operated as a self-hosted AI product rather than just a personal playground. The app emphasizes cross-device conversation sync and sharing without requiring extra services like WebDAV, aiming to reduce setup friction for end users and increase retention for operators. ... -
11
FinRobot
An Open-Source AI Agent Platform for Financial Analysis using LLMs
FinRobot is an open-source AI framework focused on automating financial data workflows by combining data ingestion, feature engineering, model training, and automated decision-making pipelines tailored for quantitative finance applications. It provides developers and quants with structured modules to fetch market data, process time series, generate technical indicators, and construct features appropriate for machine learning models, while also supporting backtesting and evaluation metrics to measure strategy performance. ... -
12
Lingvo
Framework for building neural networks
Lingvo is a TensorFlow based framework focused on building and training sequence models, especially for language and speech tasks. It was originally developed for internal research and later open sourced to support reproducible experiments and shared model implementations. The framework provides a structured way to define models, input pipelines, and training configurations using a common interface for layers, which encourages reuse across different tasks. It has been used to implement state of the art architectures such as recurrent neural networks, Transformer models, variational autoencoder hybrids, and multi task systems. ... -
13
MCPJungle
Self-hosted MCP Gateway and Registry for AI agents
MCPJungle is a self-hosted gateway and registry for the Model Context Protocol (MCP), aimed at managing tool/integration servers for AI agents within organizations. It offers a “single source of truth” registry where developers can register MCP servers and the tools they provide, and MCP clients (such as AI agents) discover and consume those tools through one gateway endpoint. This greatly simplifies the architecture when you have many MCP servers; agents only need to connect to one gateway rather than multiple endpoints. ... -
14
HunyuanWorld-Mirror
Fast and Universal 3D reconstruction model for versatile tasks
HunyuanWorld-Mirror focuses on fast, universal 3D reconstruction that can ingest varied inputs and produce multiple kinds of 3D outputs. The model accepts combinations of images, camera intrinsics and poses, or even depth cues, then reconstructs consistent 3D geometry suitable for downstream rendering or editing. The pipeline emphasizes both speed and flexibility so creators can go from casual captures to assets without elaborate capture rigs. Outputs can include point clouds, estimated camera parameters, and other 3D representations that plug into typical graphics workflows. ... -
15
nanochat
The best ChatGPT that $100 can buy
...The repository stitches together every stage of the lifecycle: tokenizer training, pretraining a Transformer on a large web corpus, mid-training on dialogue and multiple-choice tasks, supervised fine-tuning, optional reinforcement learning for alignment, and finally efficient inference with caching. Its north star is approachability and speed: you can boot a fresh GPU box and drive the whole pipeline via a single script, producing a usable chat model in hours and a clear markdown report of what happened. The code is written to be read—concise training loops, transparent configs, and minimal wrappers—so you can audit each step, tweak it, and rerun without getting lost in framework indirection. -
16
DBHub
Universal database MCP server connecting to MySQL, PostgreSQL
DBHub is a universal database gateway that implements the MCP server interface so assistants and IDEs can explore and query databases through typed tools. It supports multiple transports—stdio for desktop clients and HTTP for networked scenarios—making it flexible to embed or deploy. Configuration is environment-variable driven, with a DSN and per-engine settings covering Postgres, MySQL, MariaDB, SQL Server, and SQLite. Operational flags include read-only mode, row limits, and even SSH... -
17
MetaMCP
MCP Aggregator, Orchestrator, Middleware, Gateway in one docker
MetaMCP is an all-in-one MCP aggregator, orchestrator, and middleware that merges many MCP servers into a single, policy-aware server you can point any MCP client at. It’s built to centralize discovery, apply middlewares (e.g., auth, rate limits, transforms), and present a unified catalog of tools and resources from diverse backends. The repository and site describe it as “the one MCP to manage all your MCPs,” with diagrams and examples showing how to compose fleets behind a single endpoint.... -
18
MCP Shrimp Task Manager
Shrimp Task Manager is a task tool built for AI Agents
Shrimp Task Manager is an MCP server that converts natural-language requests into structured development tasks with dependencies, status, and style/format rules—built for agents that reason step-by-step. It emphasizes chain-of-thought and reflection loops, allowing an assistant to plan, refine, and re-prioritize work like a human project assistant. The server exposes typed tools so clients can create tasks, link prerequisites, record progress, and enforce writing or coding standards for... -
19
Firecrawl MCP Server
Adds powerful web scraping and search to Cursor and Claude
firecrawl-mcp-server is the official MCP integration for Firecrawl that brings high-recall web scraping, crawling, and search into IDEs and agent runtimes. It exposes tools for single-page scrape, multi-URL batch jobs, site discovery, and search enrichment, returning cleaned, structured content suitable for downstream LLM reasoning. The server is designed to run with Firecrawl’s hosted API or self-hosted deployments, making it flexible for enterprise data-governance requirements. Built-in... -
20
4M
4M: Massively Multimodal Masked Modeling
4M is a training framework for “any-to-any” vision foundation models that uses tokenization and masking to scale across many modalities and tasks. The same model family can classify, segment, detect, caption, and even generate images, with a single interface for both discriminative and generative use. The repository releases code and models for multiple variants (e.g., 4M-7 and 4M-21), emphasizing transfer to unseen tasks and modalities. Training/inference configs and issues discuss things like depth tokenizers, input masks for generation, and CUDA build questions, signaling active research iteration. ... -
21
FastVLM
This repository contains the official implementation of FastVLM
...Reported results highlight dramatic speedups in time-to-first-token and competitive quality versus contemporary open VLMs, including comparisons across small and larger variants. The repository documents model variants, showcases head-to-head numbers against known baselines, and explains how the encoder integrates with common LLM backbones. Apple’s research brief frames FastVLM as targeting real-time or latency-sensitive scenarios, where lowering visual token pressure is critical to interactive UX. In short, it’s a practical recipe to make VLMs fast without exotic token-selection heuristics. -
22
Granite 3.0 Language Models
New set of lightweight state-of-the-art, open foundation models
...The repo positions the models for both research and commercial use under an Apache-2.0 license, signaling permissive adoption paths. Documentation highlights the capability mix (reasoning, tool use, code) and points to model artifacts and guidance for evaluation. Activity on the project shows an evolving codebase with open pull requests and standard GitHub project structure for issues and security visibility. In practice, this is a hub for acquiring Granite 3.0 variants and understanding how to integrate them into applications. -
23
Granite Code Models
A Family of Open Foundation Models for Code Intelligence
...Trained on code from 116 programming languages, the family targets strong performance across diverse benchmarks while remaining accessible to the community. The repository introduces the model lineup, intended uses, and evaluation highlights, and it complements IBM’s broader Granite initiative spanning multiple modalities. IBM’s research blog details the motivation for opening these models and points developers to downloads, papers, and hosting options. Together, the materials position Granite Code as enterprise-friendly, permissively licensed models for practical software engineering assistance. ... -
24
Serena
Agent toolkit providing semantic retrieval and editing capabilities
Serena is a coding-focused agent toolkit that turns an LLM into a practical software-engineering agent with semantic retrieval and editing over real repositories. It operates as an MCP server (and other integrations), exposing IDE-like tools so agents can locate symbols, reason about code structure, make targeted edits, and validate changes. The toolkit is LLM-agnostic and framework-agnostic, positioning itself as a drop-in capability for different chat UIs, orchestrators, or custom agent... -
25
MetaCLIP
ICLR2024 Spotlight: curation/training code, metadata, distribution
...The repository provides training logic, adaptation strategies (e.g. prompt tuning, adapter modules), and evaluation across base and target domains to measure how well the model retains its general knowledge while specializing as needed. 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.
