Open Source Python AI Models - Page 9
Sort By:
Python AI Models
View 806 business solutionsBrowse free open source Python AI Models and projects below. Use the toggles on the left to filter open source Python AI Models by OS, license, language, programming language, and project status.
-
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.
-
Build Data Resilience - Take the Assessment TodayIs your recovery strategy as strong as you think? Take this quick self-assessment to check your recovery readiness and gain tailored insights. In only 2 minutes, you'll learn where you fall on the recovery readiness scale.
-
1
Consistency Models
Official repo for consistency models
consistency_models is the repository for Consistency Models, a new family of generative models introduced by OpenAI that aim to generate high-quality samples by mapping noise directly into data — circumventing the need for lengthy diffusion chains. It builds on and extends diffusion model frameworks (e.g. based on the guided-diffusion codebase), adding techniques like consistency distillation and consistency training to enable fast, often one-step, sample generation. The repo is implemented in PyTorch and includes support for large-scale experiments on datasets like ImageNet-64 and LSUN variants. It also contains checkpointed models, evaluation scripts, and variants of sampling / editing algorithms described in the paper. Because consistency models reduce the number of inference steps, they are promising for real-time or low-latency generative systems. -
2
DeepSeek MoE
Towards Ultimate Expert Specialization in Mixture-of-Experts Language
DeepSeek-MoE (“DeepSeek MoE”) is the DeepSeek open implementation of a Mixture-of-Experts (MoE) model architecture meant to increase parameter efficiency by activating only a subset of “expert” submodules per input. The repository introduces fine-grained expert segmentation and shared expert isolation to improve specialization while controlling compute cost. For example, their MoE variant with 16.4B parameters claims comparable or better performance to standard dense models like DeepSeek 7B or LLaMA2 7B using about 40% of the total compute. The repo publishes both Base and Chat variants of the 16B MoE model (deepseek-moe-16b) and provides evaluation results across benchmarks. It also includes a quick start with inference instructions (using Hugging Face Transformers) and guidance on fine-tuning (DeepSpeed, hyperparameters, quantization). The licensing is MIT for code, with a “Model License” applied to the models. -
3
DeepSeek-V3.2
High-efficiency reasoning and agentic intelligence model
DeepSeek-V3.2 is a cutting-edge large language model developed by DeepSeek-AI, focused on achieving high reasoning accuracy and computational efficiency for agentic tasks. It introduces DeepSeek Sparse Attention (DSA), a new attention mechanism that dramatically reduces computational overhead while maintaining strong long-context performance. Built with a scalable reinforcement learning framework, it reaches near-GPT-5 levels of reasoning and outperforms comparable models like DeepSeek-V3.1 and Gemini-3.0-Pro in advanced benchmarks. The model was notably used in competitive AI challenges such as the 2025 International Mathematical Olympiad (IMO) and IOI, achieving top-tier results. DeepSeek-V3.2 also features a large-scale agentic task synthesis pipeline, which generates training data to enhance tool-use intelligence and multi-step reasoning. It introduces a new “thinking with tools” chat template, allowing it to reason and decide when to invoke specific tools during problem solving. -
4
DeepSeek-V3.2-Speciale
High-compute ultra-reasoning model surpassing model surpassing GPT-5
DeepSeek-V3.2-Speciale is the high-compute, ultra-reasoning variant of DeepSeek-V3.2, designed specifically to push the boundaries of mathematical, logical, and algorithmic intelligence. It builds on the DeepSeek Sparse Attention (DSA) framework, delivering dramatically improved long-context efficiency while preserving full model quality. Unlike the standard version, Speciale is tuned exclusively for deep reasoning and therefore does not support tool-calling, focusing its full capacity on pure cognitive performance. The model uses a scaled reinforcement learning framework that allows it to surpass GPT-5 in several evaluations and reach reasoning performance comparable to Gemini-3.0-Pro. DeepSeek-V3.2-Speciale contributed to gold-medal solutions in the 2025 IMO, IOI, ICPC World Finals, and CMO, demonstrating its ability to handle elite-level problem solving. It is released under the MIT license and includes curated benchmark solutions for community verification and analysis. -
Earn up to 16% annual interest with Nexo.Generate interest, borrow against your crypto, and trade a range of cryptocurrencies — all in one platform. Geographic restrictions, eligibility, and terms apply.
-
5
DiT (Diffusion Transformers)
Official PyTorch Implementation of "Scalable Diffusion Models"
DiT (Diffusion Transformer) is a powerful architecture that applies transformer-based modeling directly to diffusion generative processes for high-quality image synthesis. Unlike CNN-based diffusion models, DiT represents the diffusion process in the latent space and processes image tokens through transformer blocks with learned positional encodings, offering scalability and superior sample quality. The model architecture parallels large language models but for image tokens—each block refines noisy latent representations toward cleaner outputs through iterative denoising steps. DiT achieves strong results on benchmarks like ImageNet and LSUN while being architecturally simple and highly modular. It supports variable resolution, conditioning on class or text embeddings, and integration with latent autoencoders (like those used in Stable Diffusion). -
6
Dia-1.6B
Dia-1.6B generates lifelike English dialogue and vocal expressions
Dia-1.6B is a 1.6 billion parameter text-to-speech model by Nari Labs that generates high-fidelity dialogue directly from transcripts. Designed for realistic vocal performance, Dia supports expressive features like emotion, tone control, and non-verbal cues such as laughter, coughing, or sighs. The model accepts speaker conditioning through audio prompts, allowing limited voice cloning and speaker consistency across generations. It is optimized for English and built for real-time performance on enterprise GPUs, though CPU and quantized versions are planned. The format supports [S1]/[S2] tags to differentiate speakers and integrates easily into Python workflows. While not tuned to a specific voice, user-provided audio can guide output style. Licensed under Apache 2.0, Dia is intended for research and educational use, with explicit restrictions on misuse like identity mimicry or deceptive content. -
7
DreamCraft3D
Official implementation of DreamCraft3D
DreamCraft3D is DeepSeek’s generative 3D modeling framework / model family that likely extends their earlier 3D efforts (e.g. Shap-E or Point-E style models) with more capability, control, or expression. The name suggests a “dream crafting” metaphor—users probably supply textual or image prompts and generate 3D assets (point clouds, meshes, scenes). The repository includes model code, inference scripts, sample prompts, and possibly dataset preparation pipelines. It may integrate rendering or post-processing modules (e.g. mesh smoothing, texturing) to make the outputs more output-ready. Because 3D generation is hardware‐intensive, the repository likely also includes optimizations like quantization, pruning, or inference accelerations (e.g. using FlashMLA or DeepEP) to make the generation pipeline faster or more efficient. DreamCraft3D may also support style or attribute control (e.g. “make this object metallic,” “add textures”) via prompt conditioning or guides. -
8
FastVLM
This repository contains the official implementation of FastVLM
FastVLM is an efficiency-focused vision-language modeling stack that introduces FastViTHD, a hybrid vision encoder engineered to emit fewer visual tokens and slash encoding time, especially for high-resolution images. Instead of elaborate pruning stages, the design trades off resolution and token count through input scaling, simplifying the pipeline while maintaining strong accuracy. 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. -
9
FastViT
This repository contains the official implementation of research
FastViT is an efficient vision backbone family that blends convolutional inductive biases with transformer capacity to deliver strong accuracy at mobile and real-time inference budgets. Its design pursues a favorable latency-accuracy Pareto curve, targeting edge devices and server scenarios where throughput and tail latency matter. The models use lightweight attention and carefully engineered blocks to minimize token mixing costs while preserving representation power. Training and inference recipes highlight straightforward integration into common vision tasks such as classification, detection, and segmentation. The codebase provides reference implementations and checkpoints that make it easy to evaluate or fine-tune on downstream datasets. In practice, FastViT offers drop-in backbones that reduce compute and memory pressure without exotic training tricks. -
AI-generated apps that pass security reviewRetool lets you generate dashboards, admin panels, and workflows directly on your data. Type something like “Build me a revenue dashboard on my Stripe data” and get a working app with security, permissions, and compliance built in from day one. Whether on our cloud or self-hosted, create the internal software your team needs without compromising enterprise standards or control.
-
10
FireRedASR
Open-source industrial-grade ASR models
FireRedASR is an industrial-grade family of open-source automatic speech recognition models designed to provide high-precision speech-to-text performance across languages including Mandarin, English, and various Chinese dialects, achieving new state-of-the-art benchmarks on public test sets. The project includes multiple model variants to meet different application needs, such as high-accuracy end-to-end interaction using an encoder-adapter-LLM framework and efficient real-time recognition using attention-based encoder-decoder architectures, giving developers flexibility in balancing performance and resource constraints. FireRedASR not only excels in traditional speech recognition tasks but also demonstrates strong capability in challenging scenarios like singing lyrics recognition, where accurate transcription is often difficult for conventional models. -
11
FireRedTTS-2
Long-form streaming TTS system for multi-speaker dialogue generation
FireRedTTS2 is a next-generation open-source text-to-speech (TTS) system focused on long-form, streaming speech synthesis for multi-speaker dialogue, delivering stable natural speech with context-aware prosody and reliable speaker transitions that support real-time and conversational applications. It features a specialized streaming speech tokenizer and a dual-transformer architecture that enables low latency and high-quality synthesis, making it suitable for interactive systems like chatbots, podcasts, and applications where dynamic turn-taking between speakers is essential. FireRedTTS2 supports multilingual output and speaker flexibility, enabling scenarios that involve language switching, cross-lingual voice cloning, and expressive dialogue generation that maintains consistency over longer utterances. -
12
FixRes
Reproduces results of "Fixing the train-test resolution discrepancy"
FixRes is a lightweight yet powerful training methodology for convolutional neural networks (CNNs) that addresses the common train-test resolution discrepancy problem in image classification. Developed by Facebook Research, FixRes improves model generalization by adjusting training and evaluation procedures to better align input resolutions used during different phases. The approach is simple but highly effective, requiring no architectural modifications and working across diverse CNN backbones such as ResNet, ResNeXt, PNASNet, and EfficientNet. FixRes demonstrates that a mismatch between training and testing resolutions often leads to suboptimal accuracy, and fine-tuning the classifier and batch normalization layers at higher test resolutions significantly enhances performance. The repository includes pretrained models, feature embeddings, and evaluation scripts corresponding to the experiments reported in the NeurIPS 2019 paper “Fixing the train-test resolution discrepancy.” -
13
GLIDE (Text2Im)
GLIDE: a diffusion-based text-conditional image synthesis model
glide-text2im is an open source implementation of OpenAI’s GLIDE model, which generates photorealistic images from natural language text prompts. It demonstrates how diffusion-based generative models can be conditioned on text to produce highly detailed and coherent visual outputs. The repository provides both model code and pretrained checkpoints, making it possible for researchers and developers to experiment with text-to-image synthesis. GLIDE includes advanced techniques such as classifier-free guidance, which improves the quality and alignment of generated images with the input text. The project also offers sampling scripts and utilities for exploring how diffusion models can be applied to multimodal tasks. As one of the early diffusion-based text-to-image systems, glide-text2im laid important groundwork for later advances in generative AI research. -
14
GLM-4.6V
GLM-4.6V/4.5V/4.1V-Thinking, towards versatile multimodal reasoning
GLM-4.6V represents the latest generation of the GLM-V family and marks a major step forward in multimodal AI by combining advanced vision-language understanding with native “tool-call” capabilities, long-context reasoning, and strong generalization across domains. Unlike many vision-language models that treat images and text separately or require intermediate conversions, GLM-4.6V allows inputs such as images, screenshots or document pages directly as part of its reasoning pipeline — and can output or act via tools seamlessly, bridging perception and execution. Its architecture supports a very large context window (on the order of 128K tokens during training), which lets it handle complex multimodal inputs like long documents, multi-page reports, or video transcripts, while maintaining coherence across extended content. In benchmarks and internal evaluations, GLM-4.6V achieves state-of-the-art (SoTA) performance among models of comparable parameter scale on multimodal reasoning. -
15
GLM-V
GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning
GLM-V is an open-source vision-language model (VLM) series from ZhipuAI that extends the GLM foundation models into multimodal reasoning and perception. The repository provides both GLM-4.5V and GLM-4.1V models, designed to advance beyond basic perception toward higher-level reasoning, long-context understanding, and agent-based applications. 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. -
16
GPT2-Pytorch with Text-Generator
Simple Text-Generator with OpenAI gpt-2 Pytorch Implementation
GPT-2 PyTorch is a compact educational implementation of OpenAI’s GPT-2 text generator in PyTorch. It uses pretrained weights converted for PyTorch rather than training the language model from scratch. Users can begin generation from a supplied prompt or request unconditional samples. Command-line options control sample count, batch size, output length, temperature, and top-k filtering. The repository includes a runnable Python script, dependency file, and Google Colab notebook for faster experimentation. It is best suited to studying an early Transformer language model and its sampling process rather than building a modern production system. -
17
Gorden Super PPT Skills
AI PPT Track Terminator, the strongest PPT Skill ever
Gorden Super PPT Skills is an AI presentation skill package for generating high-density visual presentations and converting them into editable PowerPoint files. The workflow is split into three skills that can be used separately or together. One skill generates image-based presentation pages from a topic or content brief. Another skill reconstructs image slides into editable PPTX files by separating backgrounds, layout structures, icons, decorations, and text. The orchestration skill chains both steps so users can create a polished visual deck and then recover an editable version. It is designed for Codex-based workflows and is useful for users who want more elaborate slide design than standard text-to-PPT generators provide. -
18
Granite TSFM
Foundation Models for Time Series
granite-tsfm collects public notebooks, utilities, and serving components for IBM’s Time Series Foundation Models (TSFM), giving practitioners a practical path from data prep to inference for forecasting and anomaly-detection use cases. The repository focuses on end-to-end workflows: loading data, building datasets, fine-tuning forecasters, running evaluations, and serving models. It documents the currently supported Python versions and points users to where the core TSFM models are hosted and how to wire up service components. Issues and examples in the tracker illustrate common tasks such as slicing inference windows or using pipeline helpers that return pandas DataFrames, grounding the library in day-to-day time-series operations. 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. -
19
HRM-Text
1B text generation model based on the HRM architecture
HRM-Text is a one-billion-parameter text generation model and pretraining framework based on the Hierarchical Reasoning Model architecture. It is designed to make foundation model pretraining more accessible by reducing compute and data requirements compared with traditional scaling-heavy approaches. The system combines hierarchical recurrent design, task-completion strengthening, and latent-space reasoning. Its training stack includes PrefixLM sequence packing, FlashAttention 3 kernels, PyTorch FSDP2, evaluation scripts, and checkpoint conversion tools. The repository supports reference pretraining runs for smaller and larger configurations, with Hopper-class GPUs expected for the attention path. It is useful for researchers and engineers exploring efficient language model pretraining, reasoning-focused architectures, and reproducible foundation model experiments. -
20
HiDream-I1
Open-source image generative foundation model
HiDream-I1 is an open-source image generation foundation model with 17 billion parameters. It is designed to produce high-quality images from text prompts while keeping inference practical through efficient model design. The project provides full, dev, and fast model variants with different inference step counts. It supports direct Python inference scripts, an interactive Gradio demo, and integration through the Hugging Face Diffusers library. The model uses a Llama 3.1 text encoder path and requires the proper Hugging Face access setup for automatic downloads. It is useful for researchers, developers, and creative AI builders who want an open text-to-image model with strong benchmark performance and multiple deployment options. -
21
Hunyuan-MT-7B
Tencent’s 36-language state-of-the-art translation model
Hunyuan-MT-7B is a large-scale multilingual translation model developed by Tencent, designed to deliver state-of-the-art translation quality across 36 languages, including several Chinese ethnic minority languages. It forms part of the Hunyuan Translation Model family, alongside Hunyuan-MT-Chimera, which ensembles outputs for even higher accuracy. Trained with a comprehensive framework spanning pretraining, cross-lingual pretraining, supervised fine-tuning, enhancement, and ensemble refinement, the model achieves competitive results against systems of similar or larger scale. At WMT25, Hunyuan-MT secured first place in 30 of the 31 translation categories it entered, highlighting its reliability in real-world multilingual use. The model offers flexible deployment options with variants such as FP8 quantization and ensemble configurations. It supports natural prompts for both Chinese translations, making it easy to integrate into translation workflows. -
22
HunyuanCustom
Multimodal-Driven Architecture for Customized Video Generation
HunyuanCustom is a multimodal video customization framework by Tencent Hunyuan, aimed at generating customized videos featuring particular subjects (people, characters) under flexible conditions, while maintaining subject/identity consistency. It supports conditioning via image, audio, video, and text, and can perform subject replacement in videos, generate avatars speaking given audio, or combine multiple subject images. The architecture builds on HunyuanVideo, with added modules for identity reinforcement and modality-specific condition injection. Text-image fusion module based on LLaVA for improved multimodal understanding. Applicable to single- and multi-subject scenarios, video editing/replacement, singing avatars etc. -
23
HunyuanDiT
Diffusion Transformer with Fine-Grained Chinese Understanding
HunyuanDiT is a high-capability text-to-image diffusion transformer with bilingual (Chinese/English) understanding and multi-turn dialogue capability. It trains a diffusion model in latent space using a transformer backbone and integrates a Multimodal Large Language Model (MLLM) to refine captions and support conversational image generation. It supports adapters like ControlNet, IP-Adapter, LoRA, and can run under constrained VRAM via distillation versions. LoRA, ControlNet (pose, depth, canny), IP-adapter to extend control over generation. Integration with Gradio for web demos and diffusers / command-line compatibility. Supports multi-turn T2I (text-to-image) interactions so users can iteratively refine their images via dialogue. -
24
HunyuanVideo-Avatar
Tencent Hunyuan Multimodal diffusion transformer (MM-DiT) model
HunyuanVideo-Avatar is a multimodal diffusion transformer (MM-DiT) model by Tencent Hunyuan for animating static avatar images into dynamic, emotion-controllable, and multi-character dialogue videos, conditioned on audio. It addresses challenges of motion realism, identity consistency, and emotional alignment. Innovations include a character image injection module, an Audio Emotion Module for transferring emotion cues, and a Face-Aware Audio Adapter to isolate audio effects on faces, enabling multiple characters to be animated in a scene. Character image injection module for better consistency between training and inference conditioning. Emotion control by extracting emotion reference images and transferring emotional style into video sequences. -
25
Hy-MT2 is a family of fast-thinking multilingual translation models built for complex real-world translation scenarios. It includes 1.8B, 7B, and 30B-A3B model sizes, giving users options for lightweight deployment, stronger general performance, or MoE-based capacity. The models support translation across 33 languages and are designed to follow detailed translation instructions in multiple languages. They can handle tasks involving terminology, style, personalization, delimiters, structured data, and background-aware translation. The repository also provides model links, inference guidance, deployment examples, training documentation, and quantization resources. Overall, Hy-MT2 is useful for developers and researchers who need flexible, instruction-following machine translation models for production, evaluation, or experimentation.
