Search Results for "training" - Page 16
Sort By:
Showing 890 open source projects for "training"
View related business solutions-
$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.
-
Stop Storing Third-Party Tokens in Your DatabaseRolling your own OAuth token storage can be a security liability. Token Vault securely stores access and refresh tokens from federated providers and handles exchange and renewal automatically. Connected accounts, refresh exchange, and privileged worker flows included.
-
1
Tracking Any Point (TAP)
DeepMind model for tracking arbitrary points across videos & robotics
TAPNet is the official Google DeepMind repository for Tracking Any Point (TAP), bundling datasets, models, benchmarks, and demos for precise point tracking in videos. The project includes the TAP-Vid and TAPVid-3D benchmarks, which evaluate long-range tracking of arbitrary points in 2D and 3D across diverse real and synthetic videos. Its flagship models—TAPIR, BootsTAPIR, and the latest TAPNext—use matching plus temporal refinement or next-token style propagation to achieve state-of-the-art... -
2
GLM-V
GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning
...GLM-4.5V builds on the flagship GLM-4.5-Air foundation (106B parameters, 12B active), achieving state-of-the-art results on 42 benchmarks across image, video, document, GUI, and grounding tasks. It introduces hybrid training for broad-spectrum reasoning and a Thinking Mode switch to balance speed and depth of reasoning. GLM-4.1V-9B-Thinking incorporates reinforcement learning with curriculum sampling (RLCS) and Chain-of-Thought reasoning, outperforming models much larger in scale (e.g., Qwen-2.5-VL-72B) across many benchmarks. -
3
SuperDuperDB
Integrate, train and manage any AI models and APIs with your database
Build and manage AI applications easily without needing to move your data to complex pipelines and specialized vector databases. Integrate AI and vector search directly with your database including real-time inference and model training. Just using Python. A single scalable deployment of all your AI models and APIs which is automatically kept up-to-date as new data is processed immediately. No need to introduce an additional database and duplicate your data to use vector search and build on top of it. SuperDuperDB enables vector search in your existing database. ... -
4
MiniCPM4.1
Achieving 3+ generation speedup on reasoning tasks
MiniCPM4.1 is an enhanced iteration of the MiniCPM4 architecture, introducing improvements in reasoning capabilities, inference speed, and hybrid operation modes that allow dynamic switching between deep reasoning and standard generation. It builds upon the same efficiency-focused philosophy but further optimizes decoding performance, achieving substantial speed gains in reasoning-intensive tasks while maintaining high-quality outputs. One of its key innovations is the hybrid reasoning mode,... -
Gemini 3 and 200+ AI Models on One PlatformBuild, govern, and optimize agents and models with Gemini Enterprise Agent Platform.
-
5
Made With ML
Learn how to develop, deploy and iterate on production-grade ML
Made-With-ML is an open-source educational repository and course designed to teach developers how to build production-grade machine learning systems using modern MLOps practices. The project focuses on bridging the gap between experimental machine learning notebooks and real-world software systems that can be deployed, monitored, and maintained at scale. It provides structured lessons and practical code examples that demonstrate how to design machine learning workflows, manage datasets,... -
6
Text-to-LoRA (T2L)
Hypernetworks that adapt LLMs for specific benchmark tasks
Text-to-LoRA is a research project that introduces a method for dynamically adapting large language models using hypernetworks that generate LoRA parameters directly from textual descriptions. Instead of training a new LoRA adapter for every task or dataset, the system can produce task-specific adaptations based solely on a text description of the desired capability. This approach enables models to rapidly internalize new contextual knowledge without performing traditional fine-tuning steps. The project provides a reference implementation of the Doc-to-LoRA method, which allows language models to quickly encode factual information or contextual constraints into lightweight LoRA modules. ... -
7
LLMSurvey
A Survey of Large Language Models
...The project is closely associated with the academic survey titled “A Survey of Large Language Models,” which provides a comprehensive overview of the development, architecture, capabilities, and societal implications of modern LLMs. The repository organizes hundreds of research papers into thematic sections that reflect the main areas of LLM research, including model architectures, training strategies, evaluation benchmarks, alignment techniques, and downstream applications. By structuring the literature in a navigable format, LLMSurvey allows researchers and practitioners to quickly explore important publications in the field without manually searching through multiple databases. -
8
TurboDiffusion
100–200× Acceleration for Video Diffusion Models
TurboDiffusion is an advanced open-source framework designed to dramatically accelerate video diffusion model generation, aiming for performance improvements on the order of 100–200× compared with traditional implementations while retaining high output quality. It achieves this by combining a suite of algorithmic and engineering optimizations, including attention acceleration techniques, efficient step distillation methods, and quantization strategies that reduce computational overhead. The... -
9
NitroGen
A Foundation Model for Generalist Gaming Agents
NitroGen is a foundation model for generalist gaming agents developed under the MineDojo initiative, aimed at training a vision-action AI that can play and interact with a wide variety of games by taking pixel inputs and predicting gamepad actions. As an open research model, NitroGen is trained on extensive gameplay data spanning thousands of hours and hundreds of games to instill broad, generalizable gaming competency rather than skill at a single title. -
AI-powered service management for IT and enterprise teamsGive your IT, operations, and business teams the ability to deliver exceptional services—without the complexity. Maximize operational efficiency with refreshingly simple, AI-powered Freshservice.
-
10
Gemma in PyTorch
The official PyTorch implementation of Google's Gemma models
...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. -
11
The Hypersim Dataset
Photorealistic Synthetic Dataset for Holistic Indoor Scene
...It provides richly annotated renderings—RGB, depth, surface normals, instance and semantic segmentations, and material/lighting metadata—produced from high-fidelity virtual environments. The dataset spans diverse furniture layouts, room types, and camera trajectories, enabling robust training for geometry, segmentation, and SLAM-adjacent tasks. Rendering pipelines and utilities allow researchers to reproduce sequences, generate novel views, or extract task-specific supervision. Because the data are perfectly labeled and controllable, Hypersim is well suited for pretraining and for studying domain transfer to real imagery. ... -
12
Godot RL Agents
An Open Source package that allows video game creators
godot_rl_agents is a reinforcement learning integration for the Godot game engine. It allows AI agents to learn how to interact with and play Godot-based games using RL algorithms. The toolkit bridges Godot with Python-based RL libraries like Stable-Baselines3, making it possible to create complex and visually rich RL environments natively in Godot. -
13
Kubeflow pipelines
Machine Learning Pipelines for Kubeflow
...A pipeline component is a self-contained set of user code, packaged as a Docker image, that performs one step in the pipeline. For example, a component can be responsible for data preprocessing, data transformation, model training, and so on. -
14
PML
The easiest way to use deep metric learning in your application
This library contains 9 modules, each of which can be used independently within your existing codebase, or combined together for a complete train/test workflow. To compute the loss in your training loop, pass in the embeddings computed by your model, and the corresponding labels. The embeddings should have size (N, embedding_size), and the labels should have size (N), where N is the batch size. The TripletMarginLoss computes all possible triplets within the batch, based on the labels you pass into it. Anchor-positive pairs are formed by embeddings that share the same label, and anchor-negative pairs are formed by embeddings that have different labels. ... -
15
GLM-4
GLM-4 series: Open Multilingual Multimodal Chat LMs
GLM-4 is a family of open models from ZhipuAI that spans base, chat, and reasoning variants at both 32B and 9B scales, with long-context support and practical local-deployment options. The GLM-4-32B-0414 models are trained on ~15T high-quality data (including substantial synthetic reasoning data), then post-trained with preference alignment, rejection sampling, and reinforcement learning to improve instruction following, coding, function calling, and agent-style behaviors. The... -
16
Orpheus TTS
Towards Human-Sounding Speech
Orpheus TTS is a state-of-the-art open-source text-to-speech system built on a Llama-3B backbone, treating speech synthesis as a large language model problem instead of a traditional TTS pipeline. It is designed to produce human-like speech with natural intonation, emotion, and rhythm, targeting quality comparable to or better than many closed-source systems. The project ships both pretrained and finetuned English models, as well as a family of multilingual models released as a research... -
17
Ray
A unified framework for scalable computing
...Accelerate your PyTorch and Tensorflow workload with a more resource-efficient and flexible distributed execution framework powered by Ray. Accelerate your hyperparameter search workloads with Ray Tune. Find the best model and reduce training costs by using the latest optimization algorithms. Deploy your machine learning models at scale with Ray Serve, a Python-first and framework agnostic model serving framework. Scale reinforcement learning (RL) with RLlib, a framework-agnostic RL library that ships with 30+ cutting-edge RL algorithms including A3C, DQN, and PPO. Easily build out scalable, distributed systems in Python with simple and composable primitives in Ray Core. -
18
second-brain-ai-assistant-course
Learn to build your Second Brain AI assistant with LLMs
The Second Brain AI Assistant Course is an open-source educational project designed to teach developers how to build a personal AI assistant that interacts with a user’s knowledge base. The course provides a structured curriculum that walks learners through the architecture and implementation of a production-ready AI system powered by large language models. The concept of a “second brain” refers to a personal knowledge repository containing notes, research, and documents that can be queried... -
19
RecursiveMAS
Offical Implementation for "Recursive Multi-Agent Systems"
...The system uses a lightweight module called RecursiveLink to transfer and transform latent representations between agents, enabling seamless interaction even across heterogeneous models. It also incorporates an inner–outer loop training approach that optimizes the entire system collectively rather than tuning each agent separately. This design improves efficiency, reduces token usage, and stabilizes learning during iterative reasoning. -
20
machine-learning-refined
Master the fundamentals of machine learning, deep learning
...It includes Jupyter notebooks and scripts that illustrate core machine learning topics such as regression, classification, optimization methods, and neural networks. These materials allow learners to see how algorithms behave during training and how different parameters affect model performance. -
21
TTRL
Test-Time Reinforcement Learning
TTRL is an open-source framework for test-time reinforcement learning in large language models, with a particular focus on reasoning tasks where ground-truth labels are not available during inference. The project addresses the problem of how to generate useful reward signals from unlabeled test-time data, and its central insight is that common test-time scaling practices such as majority voting can be repurposed into reward estimates for online reinforcement learning. This makes the... -
22
MiroThinker
MiroThinker is an open source deep research agent
MiroThinker is an open-source deep research AI agent designed to perform complex reasoning, information gathering, and predictive analysis tasks. The system focuses on enabling long-horizon research workflows by allowing the agent to interact repeatedly with external tools, search systems, and data sources while refining its reasoning through iterative steps. Rather than simply generating responses from a single prompt, the agent performs structured multi-step reasoning processes that... -
23
RecAI
Bridging LLM and Recommender System
...Traditional recommender systems rely on structured behavioral data such as user interactions and item embeddings, while large language models excel at understanding language and reasoning about user preferences. RecAI aims to bridge these two domains by creating architectures and training methods that allow LLMs to function as intelligent recommendation engines. The project explores several approaches, including fine-tuning language models using user behavior data, building recommender agents, and using LLMs to explain recommendation results. RecAI also investigates how conversational interfaces powered by LLMs can improve the personalization and transparency of recommendation systems. -
24
Wan Move
Motion-controllable Video Generation via Latent Trajectory Guidance
...Wan-Move is particularly notable for eliminating the need for additional motion encoders, instead directly infusing motion cues into spatiotemporal features, which simplifies both training and inference. -
25
DevOps Exercises
Linux, Jenkins, AWS, SRE, Prometheus, Docker, Python, Ansible, Git
DevOps Exercises is a massive, community-maintained collection of questions, tasks, and mini-challenges that cover the breadth of modern DevOps and platform engineering. It spans Linux, networking, Docker, Kubernetes, CI/CD, monitoring, cloud providers, security, and even soft skills and troubleshooting. The idea is to give candidates and teams a realistic practice ground for interviews, certifications, and day-to-day operational work. Because it’s structured as Q&A and exercises, you can go...
