Search Results for "training"
Sort By:
104 projects for "training" with 2 filters applied:
-
Enterprise-grade ITSM, for every businessFreshservice is an intuitive, AI-powered platform that helps IT, operations, and business teams deliver exceptional service without the usual complexity. Automate repetitive tasks, resolve issues faster, and provide seamless support across the organization. From managing incidents and assets to driving smarter decisions, Freshservice makes it easy to stay efficient and scale with confidence.
-
Add Two Lines of Code. Get Full APM.Works out of the box for Rails, Django, Express, Phoenix, and more. Monitoring exceptions and performance in no time.
-
1
DeepSeek-V3
Powerful AI language model (MoE) optimized for efficiency/performance
...It employs Multi-head Latent Attention (MLA) and the DeepSeekMoE architecture to enhance computational efficiency. The model introduces an auxiliary-loss-free load balancing strategy and a multi-token prediction training objective to boost performance. Trained on 14.8 trillion diverse, high-quality tokens, DeepSeek-V3 underwent supervised fine-tuning and reinforcement learning to fully realize its capabilities. Evaluations indicate that it outperforms other open-source models and rivals leading closed-source models, achieving this with a training duration of 55 days on 2,048 Nvidia H800 GPUs, costing approximately $5.58 million. -
2
DINOv3
Reference PyTorch implementation and models for DINOv3
...It continues the paradigm of learning strong image representations without labels using teacher–student distillation, but introduces a simplified and more scalable training recipe that performs well across datasets and architectures. DINOv3 removes the need for complex augmentations or momentum encoders, streamlining the pipeline while maintaining or improving feature quality. The model supports multiple backbone architectures, including Vision Transformers (ViT), and can handle larger image resolutions with improved stability during training. -
3
JiT
PyTorch implementation of JiT
...Rather than predicting noise, JiT models directly predict clean image data, which the research suggests aligns better with the manifold structure of natural images and leads to stronger generative performance at high resolution. This implementation supports training on large datasets like ImageNet with configurable model variants, and practical scripts for setup, training, and evaluation on GPUs are included, leveraging PyTorch’s ecosystem for real-world experimentation. The repository’s layout contains modular engine, model, and training scripts enabling researchers and engineers to customize components such as training regimes, noise schedules, and evaluation routines. -
4
DeepSeek Coder V2
DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models
DeepSeek-Coder-V2 is the version-2 iteration of DeepSeek’s code generation models, refining the original DeepSeek-Coder line with improved architecture, training strategies, and benchmark performance. While the V1 models already targeted strong code understanding and generation, V2 appears to push further in both multilingual support and reasoning in code, likely via architectural enhancements or additional training objectives. The repository provides updated model weights, evaluation results on benchmarks (e.g. ... -
$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.
-
5
DINOv2
PyTorch code and models for the DINOv2 self-supervised learning
...It builds on the DINO idea of student–teacher distillation and adapts it to modern Vision Transformer backbones with a carefully tuned recipe for data augmentation, optimization, and multi-crop training. The core promise is that a single pretrained backbone can transfer well to many downstream tasks—from linear probing on classification to retrieval, detection, and segmentation—often requiring little or no fine-tuning. The repository includes code for training, evaluating, and feature extraction, with utilities to run k-NN or linear evaluation baselines to assess representation quality. ... -
6
DeepSeek R1
Open-source, high-performance AI model with advanced reasoning
...The model employs a Mixture of Experts (MoE) architecture, comprising 671 billion total parameters with 37 billion active parameters per token, and supports a context length of up to 128,000 tokens. DeepSeek-R1's training regimen uniquely integrates large-scale reinforcement learning (RL) without relying on supervised fine-tuning, enabling the model to develop advanced reasoning capabilities. This approach has resulted in performance comparable to leading models like OpenAI's o1, while maintaining cost-efficiency. To further support the research community, DeepSeek has released distilled versions of the model based on architectures such as LLaMA and Qwen. -
7
MobileCLIP
Implementation of "MobileCLIP" CVPR 2024
...A companion “mobileclip-dr” repository details large-scale, distributed data-generation pipelines used to reinforce datasets across billions of samples on thousands of GPUs. Overall, MobileCLIP emphasizes end-to-end practicality: scalable training, deployable models, and consumer-grade demos. -
8
Hunyuan3D-2.1
From Images to High-Fidelity 3D Assets
Hunyuan3D-2.1 is Tencent Hunyuan’s advanced 3D asset generation system that produces high-fidelity 3D models with Physically Based Rendering (PBR) textures. It is fully open-source with released model weights, training, and inference code. It improves on prior versions by using a PBR texture pipeline (enabling realistic material effects like reflections and subsurface scattering) and allowing community fine-tuning and extension. It supports both shape generation (mesh geometry) and texture generation modules. Physically Based Rendering texture synthesis to model realistic material effects, including reflections, subsurface scattering, etc. ... -
9
Step3-VL-10B
Multimodal model achieving SOTA performance
...Despite having only about 10 billion parameters, it delivers performance that rivals or even surpasses much larger models (10×–20× larger) on a wide range of multimodal benchmarks covering reasoning, perception, and complex tasks, positioning it as one of the most powerful models in its class. It achieves this efficiency and strong performance through unified pre-training on a massive 1.2 trillion-token multimodal corpus that jointly optimizes a language-aligned perception encoder with a powerful decoder, creating deep synergy between image processing and text understanding. -
Gemini 3 and 200+ AI Models on One PlatformBuild, govern, and optimize agents and models with Gemini Enterprise Agent Platform.
-
10
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. -
11
Mistral Finetune
Memory-efficient and performant finetuning of Mistral's models
mistral-finetune is an official lightweight codebase designed for memory-efficient and performant finetuning of Mistral’s open models (e.g. 7B, instruct variants). It builds on techniques like LoRA (Low-Rank Adaptation) to allow customizing models without full parameter updates, which reduces GPU memory footprint and training cost. The repo includes utilities for data preprocessing (e.g. reformat_data.py), validation scripts, and example YAML configs for training variants like 7B base or instruct models. It supports function-calling style datasets (via "messages" keys) as well as plain text formats, with guidelines on formatting, tokenization, and vocabulary extension (e.g. extending vocab to 32768 for some models) before finetuning. ... -
12
HunyuanVideo-I2V
A Customizable Image-to-Video Model based on HunyuanVideo
...It extends video generation so that given a static reference image plus an optional prompt, it generates a video sequence that preserves the reference image’s identity (especially in the first frame) and allows stylized effects via LoRA adapters. The repository includes pretrained weights, inference and sampling scripts, training code for LoRA effects, and support for parallel inference via xDiT. Resolution, video length, stability mode, flow shift, seed, CPU offload etc. Parallel inference support using xDiT for multi-GPU speedups. LoRA training / fine-tuning support to add special effects or customize generation. -
13
NVIDIA Isaac GR00T
NVIDIA Isaac GR00T N1.5 is the world's first open foundation model
...It accepts multimodal inputs—such as language and images—and uses a diffusion transformer architecture built upon vision-language encoders, enabling adaptive robot behaviors across diverse environments. It is designed to be customizable via post-training with real or synthetic data. The vision-language model remains frozen during both pretraining and finetuning, preserving language understanding and improving generalization. Streamlined MLP connection between vision encoder and LLM with added layer normalization. -
14
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... -
15
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. ... -
16
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. ... -
17
GLM-5
From Vibe Coding to Agentic Engineering
GLM-5 is a next-generation open-source large language model (LLM) developed by the Z .ai team under the zai-org organization that pushes the boundaries of reasoning, coding, and long-horizon agentic intelligence. Building on earlier GLM series models, GLM-5 dramatically scales the parameter count (to roughly 744 billion) and expands pre-training data to significantly improve performance on complex tasks such as multi-step reasoning, software engineering workflows, and agent orchestration compared to its predecessors like GLM-4.5. It incorporates innovations like DeepSeek Sparse Attention (DSA) to preserve massive context windows while reducing deployment costs and supporting long context processing, which is crucial for detailed plans and agent tasks. -
18
Sapiens
High-resolution models for human tasks
...It includes simulation environments, datasets, and benchmarks for testing grounded understanding, imitation learning, and decision-making. The system’s modular pipeline supports both imitation-based and reinforcement-based training strategies, allowing flexible experimentation with different embodiments and tasks. -
19
HY-World 1.5
A Systematic Framework for Interactive World Modeling
...It aims to empower AI agents with the capability to both understand and generate multimedia content — including text, audio, image, and potentially 3D or game-world elements — enabling lifelike dialogue, environmental interpretations, and responsive world behavior. The platform targets use cases in digital entertainment, game worlds, training simulators, and interactive storytelling, where AI agents need to adapt to real-time user inputs and changes in environment state. It blends advanced reasoning with multimodal synthesis, enabling agents to describe scenes, generate context-appropriate responses, and contribute to narrative or gameplay flows. The underlying framework typically supports large-context state tracking across extended interactions, blending temporal and spatial multimodal signals. -
20
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. -
21
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 architecture design strategies. The model family includes variants like a foundational base model that researchers can fine-tune for specific use cases and an instruct-optimized variant primed for general-purpose chat and agent-style interactions, offering flexibility for both experimentation and deployment. ... -
22
OpenTinker
OpenTinker is an RL-as-a-Service infrastructure for foundation models
...Traditional RL setups can be monolithic and difficult to configure, but OpenTinker separates concerns across agent definition, environment interaction, and execution, which lets developers focus on defining the logic of agents and environments separately from how training and inference are run. 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. -
23
SlowFast
Video understanding codebase from FAIR for reproducing video models
...The architecture is modular and supports tasks like action recognition, temporal localization, and video segmentation, performing strongly on benchmarks like Kinetics and AVA. The repository provides training recipes, pretrained models, and distributed pipelines optimized for large-scale video datasets. -
24
CLIP
CLIP, Predict the most relevant text snippet given an image
...It was trained on large sets of (image, caption) pairs using a contrastive objective: images and their matching text are pulled together in embedding space, while mismatches are pushed apart. Once trained, you can give it any text labels and ask it to pick which label best matches a given image—even without explicit training for that classification task. The repository provides code for model architecture, preprocessing transforms, evaluation pipelines, and example inference scripts. Because it generalizes to arbitrary labels via text prompts, CLIP is a powerful tool for tasks that involve interpreting images in terms of descriptive language. -
25
HeartMuLa
A Family of Open Sourced Music Foundation Models
...The project also includes HeartCodec, a music codec optimized for high reconstruction fidelity, enabling efficient tokenization and reconstruction workflows that are critical for training and generation pipelines. For text extraction from audio, it provides HeartTranscriptor, a Whisper-based model tuned specifically for lyrics transcription, which helps bridge generated or recorded audio back into structured text. It also introduces HeartCLAP, which aligns audio and text into a shared embedding space.
