Search Results for "training" - Page 8
Sort By:
Showing 890 open source projects for "training"
View related business solutions-
Gemini 3 and 200+ AI Models on One PlatformBuild, govern, and optimize agents and models with Gemini Enterprise Agent Platform.
-
$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
ShoppingAgent
Custom Chinese chatbot with Seq2Seq, GPT, and agent features
...In addition to core chatbot functionality, the project introduces agent-based capabilities, enabling practical use cases like automated workflows and task-oriented assistants. It also includes support for small language models and local training scripts, making it accessible for users with limited computational resources. ShoppingAgent can be applied to scenarios such as customer service, question answering, and casual conversation. -
2
SeedVR
Repo for SeedVR2 & SeedVR
...The project includes both the original SeedVR and its successor SeedVR2 models, which are designed to restore degraded or low-quality video content by learning to reconstruct high-fidelity frames with temporal coherence. These models leverage advanced techniques such as adaptive attention mechanisms and adversarial training to produce visually appealing results in a single inference step, pushing the boundaries of video restoration research. SeedVR’s transformer-based design allows it to handle variable frame resolutions and lengths, and its architecture is optimized to overcome traditional limitations of windowed attention in high-resolution contexts. -
3
Vision Transformer Pytorch
Implementation of Vision Transformer, a simple way to achieve SOTA
...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. It’s widely used as an educational reference for people learning transformers in vision and as a lightweight baseline for research prototypes. The project encourages experimentation—swap optimizers, change augmentations, or plug the transformer backbone into downstream tasks. -
4
Anomalib
An anomaly detection library comprising state-of-the-art algorithms
Anomalib is an open-source deep learning library focused on anomaly detection and localization tasks, collecting state-of-the-art algorithms and tools under one modular framework. It provides implementations of leading anomaly detection methods drawn from current research, as well as a full set of utilities for training, evaluating, benchmarking, and deploying these models on both public and private datasets. Anomalib emphasizes flexibility and reproducibility: you can use its simple APIs to plug in custom models, track experiments, tune hyperparameters, and generate visualizations that highlight anomalous regions. Its design supports unsupervised or semi-supervised paradigms, making it especially powerful for scenarios where only “normal” data is readily available and defects must be detected without exhaustive labeling. ... -
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
LTX-2.3
Official Python inference and LoRA trainer package
LTX-2.3 is an open-source multimodal artificial intelligence foundation model developed by Lightricks for generating synchronized video and audio from prompts or other inputs. Unlike most earlier video generation systems that only produced silent clips, LTX-2 combines video and audio generation in a unified architecture capable of producing coherent audiovisual scenes. The model uses a diffusion-transformer-based architecture designed to generate high-fidelity visual frames while... -
6
CO3D (Common Objects in 3D)
Tooling for the Common Objects In 3D dataset
...Each of the thousands of sequences in CO3Dv2 captures a common object (from categories like cars, chairs, or plants) from multiple real-world viewpoints. The dataset includes RGB images, depth maps, masks, and camera poses for each frame, along with pre-defined training, validation, and testing splits for both few-view and many-view reconstruction tasks. -
7
DeepSeek-V3.2-Exp
An experimental version of DeepSeek model
DeepSeek-V3.2-Exp is an experimental release of the DeepSeek model family, intended as a stepping stone toward the next generation architecture. The key innovation in this version is DeepSeek Sparse Attention (DSA), a sparse attention mechanism that aims to optimize training and inference efficiency in long-context settings without degrading output quality. According to the authors, they aligned the training setup of V3.2-Exp with V3.1-Terminus so that benchmark results remain largely comparable, even though the internal attention mechanism changes. In public evaluations across a variety of reasoning, code, and question-answering benchmarks (e.g. ... -
8
Implicit
Fast Python collaborative filtering for implicit feedback datasets
This project provides fast Python implementations of several different popular recommendation algorithms for implicit feedback datasets. All models have multi-threaded training routines, using Cython and OpenMP to fit the models in parallel among all available CPU cores. In addition, the ALS and BPR models both have custom CUDA kernels - enabling fitting on compatible GPU’s. This library also supports using approximate nearest neighbour libraries such as Annoy, NMSLIB and Faiss for speeding up making recommendations. -
9
IMS Toucan
Controllable and fast Text-to-Speech for over 7000 languages
IMS-Toucan is a toolkit for training, using, and teaching state-of-the-art text-to-speech systems, built at the Institute for Natural Language Processing (IMS), University of Stuttgart. It is the official home of ToucanTTS, a massively multilingual TTS system designed to support over 7,000 languages with a single unified framework. The toolkit focuses on being fast and controllable while not requiring huge amounts of compute, making it practical for research labs and smaller teams. ... -
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
10
vJEPA-2
PyTorch code and models for VJEPA2 self-supervised learning from video
...Trained representations transfer well to downstream tasks such as action recognition, temporal localization, and video retrieval, often with simple linear probes or light fine-tuning. The repository typically includes end-to-end recipes—data pipelines, augmentation policies, training scripts, and evaluation harnesses. -
11
Large Concept Model
Language modeling in a sentence representation space
Large Concept Model is a research codebase centered on concept-centric representation learning at scale, aiming to capture shared structure across many categories and modalities. It organizes training around concepts (rather than just raw labels), encouraging models to understand attributes, relations, and compositional structure that transfer across tasks. The repository provides training loops, data tooling, and evaluation routines to learn and probe these concept embeddings, typically from large image–text or weakly supervised corpora. ... -
12
HunyuanWorld-Voyager
RGBD video generation model conditioned on camera input
...At its core, Voyager integrates a world-consistent video diffusion model with an efficient long-range world exploration engine powered by auto-regressive inference. To support training, the team built a scalable data engine that automatically curates large video datasets with camera pose estimation and metric depth prediction. As a result, Voyager delivers state-of-the-art performance on world exploration benchmarks while maintaining photometric, style, and 3D consistency. -
13
Segmentation Models
Segmentation models with pretrained backbones. PyTorch
...High-level API (just two lines to create a neural network) 9 models architectures for binary and multi class segmentation (including legendary Unet) 124 available encoders (and 500+ encoders from timm) All encoders have pre-trained weights for faster and better convergence. Popular metrics and losses for training routines. All encoders have pretrained weights. Preparing your data the same way as during weights pre-training may give you better results (higher metric score and faster convergence). It is not necessary in case you train the whole model, not only the decoder. Pytorch Image Models (a.k.a. timm) has a lot of pretrained models and interface which allows using these models as encoders in smp, however, not all models are supported. ... -
14
Habitat-Lab
A modular high-level library to train embodied AI agents
...Configuring and instantiating a diverse set of embodied agents, including commercial robots and humanoids, specifying their sensors and capabilities. Providing algorithms for single and multi-agent training (via imitation or reinforcement learning, or no learning at all as in SensePlanAct pipelines), as well as tools to benchmark their performance on the defined tasks using standard metrics. -
15
LLM Action
Technical principles related to large models
LLM-Action is a knowledge/tutorial/repository that shares principles, techniques, and real-world experience related to large language models (LLMs), focusing on LLM engineering, deployment, optimization, inference, compression, and tooling. It organizes content in domains like training, inference, compression, alignment, evaluation, pipelines, and applications. Sections covering infrastructure, engineering, and deployment. Repository templates, sample code, and resource links. Articles/code on LLM compression (quantization, pruning). -
16
3D Gaussian Splatting
Original reference implementation of "3D Gaussian Splatting"
...The system represents scenes as millions of optimized 3D Gaussians rather than traditional meshes or neural fields, allowing high-quality novel view synthesis with real-time rendering performance. It includes training scripts, rendering tools, scene conversion utilities, and viewers for inspecting generated results. The project is widely used in computer graphics, spatial capture, virtual production, research, and experimental 3D reconstruction workflows. It relies on image-based reconstruction pipelines such as COLMAP to estimate camera positions before optimizing the Gaussian representation. ... -
17
SpikingJelly
SpikingJelly is an open-source deep learning framework
...This makes it especially relevant for researchers interested in biologically inspired computing, event-driven processing, and energy-efficient AI systems. The framework includes neuron models, surrogate gradient training methods, encoding strategies, network components, and utilities for simulation and experimentation, allowing users to develop a wide variety of spiking architectures. It also supports integration with familiar PyTorch workflows, which lowers the barrier for machine learning practitioners who want to explore spiking approaches without abandoning mainstream tooling. -
18
InfiniteYou
Flexible Photo Recrafting While Preserving Your Identity
...Using an architecture built around diffusion transformers (DiTs), InfiniteYou introduces a component called InfuseNet that injects identity features derived from reference images into the generation process — via residual connections — so that the output matches the person’s identity closely, without sacrificing visual quality or text-image alignment. The team uses a multi-stage training strategy with synthetic multi-sample data per identity to fine-tune for both identity consistency and aesthetic quality. Compared to prior methods, InfiniteYou significantly improves on identity similarity, text-prompt adherence, overall image quality, and avoids common problems such as face copy-pasting artifacts. -
19
YOLOv5
YOLOv5 is the world's most loved vision AI
Introducing Ultralytics YOLOv8, the latest version of the acclaimed real-time object detection and image segmentation model. YOLOv8 is built on cutting-edge advancements in deep learning and computer vision, offering unparalleled performance in terms of speed and accuracy. Its streamlined design makes it suitable for various applications and easily adaptable to different hardware platforms, from edge devices to cloud APIs. Explore the YOLOv8 Docs, a comprehensive resource designed to help... -
20
DGL
Python package built to ease deep learning on graph
Build your models with PyTorch, TensorFlow or Apache MXNet. Fast and memory-efficient message passing primitives for training Graph Neural Networks. Scale to giant graphs via multi-GPU acceleration and distributed training infrastructure. DGL empowers a variety of domain-specific projects including DGL-KE for learning large-scale knowledge graph embeddings, DGL-LifeSci for bioinformatics and cheminformatics, and many others. We are keen to bringing graphs closer to deep learning researchers. ... -
21
FL4Health
Library to facilitate federated learning research
FL4Health is a Vector Institute toolkit for building modular, clinically-focused FL pipelines. Tailored for healthcare, it supports privacy-preserving FL, heterogeneous data settings, integrated reporting, and clear API design. -
22
H2O LLM Studio
Framework and no-code GUI for fine-tuning LLMs
...You can also use H2O LLM Studio with the command line interface (CLI) and specify the configuration file that contains all the experiment parameters. To finetune using H2O LLM Studio with CLI, activate the pipenv environment by running make shell. With H2O LLM Studio, training your large language model is easy and intuitive. First, upload your dataset and then start training your model. Start by creating an experiment. You can then monitor and manage your experiment, compare experiments, or push the model to Hugging Face to share it with the community. -
23
MuseGAN
An AI for Music Generation
...This representation allows the neural network to capture rhythmic patterns, harmonic relationships, and structural dependencies across instruments. The architecture is based on convolutional GAN models that learn temporal musical structure and inter-track relationships from training data. The project was trained using the Lakh Pianoroll Dataset, a large collection of multitrack musical sequences derived from MIDI files. -
24
xLSTM
Neural Network architecture based on ideas of the original LSTM
...The architecture aims to provide competitive performance with transformer-based models while maintaining advantages such as linear computational scaling and efficient memory usage for long sequences. Researchers have demonstrated that xLSTM models can scale to billions of parameters and large training datasets while maintaining efficient inference speeds. -
25
Mathematics Dataset
This dataset code generates mathematical question and answer pairs
...The dataset enables models to learn mathematical problem-solving through examples that involve both numeric and symbolic reasoning. Version 1.0 includes over 2 million examples per category, with training splits labeled as “easy,” “medium,” and “hard,” supporting curriculum-based learning strategies. The data can be accessed via PyPI or generated locally using provided Python scripts, with outputs formatted for direct use in training or evaluation pipelines.
