Open Source Python AI Models - Page 3
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.
-
Veeam Data Platform v13.1 - Get Your Free TrialTry Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
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.
-
1
HeartMuLa
A Family of Open Sourced Music Foundation Models
HeartMuLa is the open-source library and reference implementation for the HeartMuLa family of music foundation models, designed to support both music generation and music-related understanding tasks in a cohesive stack. At the center is HeartMuLa, a music language model that generates music conditioned on inputs like lyrics and tags, with multilingual support that broadens the range of lyric-driven use cases. 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. -
2
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 GLM-Z1-32B-0414 line adds deeper mathematical, coding, and logical reasoning via extended reinforcement learning and pairwise ranking feedback, while GLM-Z1-Rumination-32B-0414 introduces a “rumination” mode that performs longer, tool-using deep research for complex, open-ended tasks. A lightweight GLM-Z1-9B-0414 brings many of these techniques to a smaller model, targeting strong reasoning under tight resource budgets. -
3
video-subtitle-generator
A GUI tool for generating subtitle from videos, generating srt files
Video Subtitle Generator is a local speech-recognition tool that creates SRT subtitle files from audio or video. It is designed to perform transcription locally without requiring users to obtain a third-party speech API. The project supports numerous languages, including Chinese, English, Korean, Japanese, Vietnamese, Russian, Spanish, and Portuguese. Users can operate it through either a graphical interface or a command-line interface. Several recognition model sizes are available, allowing users to trade GPU memory requirements for speed and accuracy. The Python-based project uses a Transformer speech-recognition approach and is designed primarily for systems with Nvidia GPUs. -
4
Chinese-LLaMA-Alpaca 2
Chinese LLaMA-2 & Alpaca-2 Large Model Phase II Project
This project is developed based on the commercially available large model Llama-2 released by Meta. It is the second phase of the Chinese LLaMA&Alpaca large model project. The Chinese LLaMA-2 base model and the Alpaca-2 instruction fine-tuning large model are open-sourced. These models expand and optimize the Chinese vocabulary on the basis of the original Llama-2, use large-scale Chinese data for incremental pre-training, and further improve the basic semantics and command understanding of Chinese. Performance improvements. The related model supports FlashAttention-2 training, supports 4K context and can be extended up to 18K+ through the NTK method. -
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
Evo 2
Genome modeling and design across all domains of life
Evo 2 is a DNA language model system designed for long-context genome modeling and biological sequence design across all domains of life. The project models DNA at single-nucleotide resolution and supports context windows of up to one million base pairs, which places it in a class of models built for very large genomic reasoning tasks. According to the repository, it uses the StripedHyena 2 architecture, was pretrained with Savanna, and was trained autoregressively on the OpenGenome2 dataset containing 8.8 trillion tokens. The codebase is focused on local inference and generation through the Vortex inference stack rather than serving as a full training framework alone, although it also points users to training and fine-tuning resources. It supports multiple ways of working with the model, including forward passes, embeddings, generation workflows, notebooks, hosted APIs, and self-hosted deployment through NVIDIA NIM. -
6
GLM-OCR
Accurate × Fast × Comprehensive
GLM-OCR is an open-source multimodal optical character recognition (OCR) model built on a GLM-V encoder–decoder foundation that brings robust, accurate document understanding to complex real-world layouts and modalities. Designed to handle text recognition, table parsing, formula extraction, and general information retrieval from documents containing mixed content, GLM-OCR excels across major benchmarks while remaining highly efficient with a relatively compact parameter size (~0.9B), enabling deployment in high-concurrency services and edge environments. The model’s multimodal capabilities allow it to reason across image and text content holistically, capturing structured and unstructured information from pages that include dense tables, seals, code snippets, and varied document graphics. GLM-OCR integrates a comprehensive SDK and inference toolchain that makes it easy for developers to install, invoke, and embed into production pipelines with simple commands or APIs. -
7
Menagerie
A collection of high-quality models for the MuJoCo physics engine
MuJoCo Menagerie, developed by Google DeepMind, is a curated collection of high-quality simulation models designed for use with the MuJoCo physics engine. It serves as a comprehensive library of accurate and ready-to-use robotic, biomechanical, and mechanical models, ensuring users can perform reliable simulations without having to build or tune models from scratch. The repository aims to improve reproducibility and quality across robotics research by providing verified models that adhere to consistent design and physical standards. Each model directory contains its 3D assets, MJCF XML definitions, licensing information, and example scenes for visualization and testing. The collection spans a wide range of categories including robotic arms, humanoids, quadrupeds, mobile manipulators, drones, and biomechanical systems. Users can access models directly via the robot_descriptions Python package or by cloning the repository for use in interactive MuJoCo simulations. -
8
TimesFM
Pretrained time-series foundation model developed by Google Research
TimesFM is a pretrained time-series foundation model from Google Research built for forecasting tasks, designed to generalize across many domains without requiring extensive per-dataset retraining. It provides a decoder-only model approach to forecasting, aiming for strong performance even in zero-shot or low-data settings where traditional models often struggle. The project includes code and an inference API intended to make it practical to run forecasts programmatically, with options to use different backends such as Torch or Flax depending on your environment and performance needs. Newer releases emphasize expanded context handling and more flexible forecasting outputs, including quantile forecasting so users can get uncertainty estimates rather than only point predictions. The repository also documents how model versions evolved, with newer variants focusing on efficiency and longer context windows while maintaining forecasting quality. -
9
Depth Pro
Sharp Monocular Metric Depth in Less Than a Second
Depth Pro is a foundation model for zero-shot metric monocular depth estimation, producing sharp, high-frequency depth maps with absolute scale from a single image. Unlike many prior approaches, it does not require camera intrinsics or extra metadata, yet still outputs metric depth suitable for downstream 3D tasks. Apple highlights both accuracy and speed: the model can synthesize a ~2.25-megapixel depth map in around 0.3 seconds on a standard GPU, enabling near real-time applications. The repo and research page emphasize boundary fidelity and crisp geometry, addressing a common weakness in monocular depth where edges can blur. Community integrations (e.g., inference wrappers and UI nodes) have sprung up around the model, reflecting practical interest in video, AR, and generative pipelines. As a general-purpose monocular depth backbone, Depth Pro slots into 3D reconstruction, relighting, and scene understanding workflows that benefit from metric predictions. -
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
GLM-4.6
Agentic, Reasoning, and Coding (ARC) foundation models
GLM-4.6 is the latest iteration of Zhipu AI’s foundation model, delivering significant advancements over GLM-4.5. It introduces an extended 200K token context window, enabling more sophisticated long-context reasoning and agentic workflows. The model achieves superior coding performance, excelling in benchmarks and practical coding assistants such as Claude Code, Cline, Roo Code, and Kilo Code. Its reasoning capabilities have been strengthened, including improved tool usage during inference and more effective integration within agent frameworks. GLM-4.6 also enhances writing quality, producing outputs that better align with human preferences and role-playing scenarios. Benchmark evaluations demonstrate that it not only outperforms GLM-4.5 but also rivals leading global models such as DeepSeek-V3.1-Terminus and Claude Sonnet 4. -
11
LingBot-World
Advancing Open-source World Models
LingBot-World is an open-source, high-fidelity world simulator designed to advance the state of world models through video generation. Built on top of Wan2.2, it enables realistic, dynamic environment simulation across diverse styles, including real-world, scientific, and stylized domains. LingBot-World supports long-term temporal consistency, maintaining coherent scenes and interactions over minute-level horizons. With real-time interactivity and sub-second latency at 16 FPS, it is well-suited for interactive applications and rapid experimentation. The project is fully open-access, releasing both code and models to help bridge the gap between closed and open world-model systems. LingBot-World empowers researchers and developers in areas such as content creation, gaming, robotics, and embodied AI learning. -
12
OpenMythos
A theoretical reconstruction of the Claude Mythos architecture
OpenMythos is an experimental, open-source implementation that attempts to reconstruct a hypothesized architecture behind advanced language models using a design called a Recurrent-Depth Transformer. The project explores the idea that instead of stacking hundreds of unique transformer layers, a smaller set of layers can be reused iteratively during inference to achieve deeper reasoning without increasing parameter count. It divides computation into three main stages, including a pre-processing phase, a looped recurrent reasoning block, and a final output refinement stage, creating a structured pipeline for inference. The architecture incorporates advanced techniques such as mixture-of-experts routing, adaptive computation time, and multiple attention mechanisms to dynamically allocate compute where needed. It is highly configurable through a centralized configuration system, allowing experimentation with different architectural parameters such as loop depth, attention type. -
13
VOID
Video Object and Interaction Deletion
VOID is an advanced AI video processing system developed by Netflix that focuses on removing objects from videos while preserving the physical and visual realism of the surrounding environment. Unlike traditional inpainting methods that only erase pixels or simple artifacts, VOID models the full interaction dynamics between objects and their environment, including shadows, reflections, and even physical consequences such as movement or balance changes. Built on top of transformer-based architectures and fine-tuned for video inpainting tasks, the system uses interaction-aware mask conditioning to ensure temporal consistency across frames. One of its most notable capabilities is its ability to simulate realistic scene behavior after object removal, such as causing an object to fall naturally if its support is removed, which significantly enhances realism. -
14
Denoiser
Real Time Speech Enhancement in the Waveform Domain (Interspeech 2020)
Denoiser is a real-time speech enhancement model operating directly on raw waveforms, designed to clean noisy audio while running efficiently on CPU. It uses a causal encoder-decoder architecture with skip connections, optimized with losses defined both in the time domain and frequency domain to better suppress noise while preserving speech. Unlike models that operate on spectrograms alone, this design enables lower latency and coherent waveform output. The implementation includes data augmentation techniques applied to the raw waveforms (e.g. noise mixing, reverberation) to improve model robustness and generalization to diverse noise types. The project supports both offline denoising (batch inference) and live audio processing (e.g. via loopback audio interfaces), making it practical for real-time use in calls or recording. The codebase includes training and evaluation scripts, configuration management via Hydra, and pretrained models on standard noise datasets. -
15
HY-Motion 1.0
HY-Motion model for 3D character animation generation
HY-Motion 1.0 is an open-source, large-scale AI model suite developed by Tencent’s Hunyuan team that generates high-quality 3D human motion from simple text prompts, enabling the automatic production of fluid, diverse, and semantically accurate animations without manual keyframing or rigging. Built on advanced deep learning architectures that combine Diffusion Transformer (DiT) and flow matching techniques, HY-Motion scales these approaches to the billion-parameter level, resulting in strong instruction-following capabilities and richer motion outputs compared to existing open-source models. The training strategy for the HY-Motion series includes extensive pre-training on thousands of hours of varied motion data, fine-tuning on curated high-quality datasets, and reinforcement learning with human feedback, which improves both the plausibility and adaptability of generated motion sequences. -
16
Qwen-Audio
Chat & pretrained large audio language model proposed by Alibaba Cloud
Qwen-Audio is a large audio-language model developed by Alibaba Cloud, built to accept various types of audio input (speech, natural sounds, music, singing) along with text input, and output text. There is also an instruction-tuned version called Qwen-Audio-Chat which supports conversational interaction (multi-round), audio + text input, creative tasks and reasoning over audio. It uses multi-task training over many different audio tasks (30+), and achieves strong multi-benchmarks performance without task-specific fine‐tuning. It includes features such as flexible multi-run chat, audio understanding/reasoning, music appreciation, and also tool usage (e.g. voice editing). -
17
Step-Video-T2V
State-of-the-art (SoTA) text-to-video pre-trained model
Step-Video-T2V is a state-of-the-art text-to-video foundation model developed to generate videos from natural-language prompts; its 30B-parameter architecture is designed to produce coherent, temporally extended video sequences — up to around 204 frames — based on input text. Under the hood it uses a compressed latent representation (a Video-VAE) to reduce spatial and temporal redundancy, and a denoising diffusion (or similar) process over that latent space to generate smooth, plausible motion and visuals. The model handles bilingual input (e.g. English and Chinese) thanks to dual encoders, and supports end-to-end text-to-video generation without requiring external assets. Its training and generation pipeline includes techniques like flow-matching, full 3D attention for temporal consistency, and fine-tuning approaches (e.g. video-based DPO) to improve fidelity and reduce artifacts. As a result, Step-Video-T2V aims to push the frontier of open-source video generation. -
18
Step1X-Edit
A SOTA open-source image editing model
Step1X-Edit is a state-of-the-art open-source image editing model/framework that uses a multimodal large language model (LLM) together with a diffusion-based image decoder to let users edit images simply via natural-language instructions plus a reference image. You supply an existing image and a textual command — e.g. “add a ruby pendant on the girl’s neck” or “make the background a sunset over mountains” — and the model interprets the instruction, computes a latent embedding combining the image content and user intent, then decodes a new image implementing the edit. The model targets general-purpose editing: from object addition/removal, style changes, recoloring, retouching, background replacement, to complex transformations like changing lighting, mood, or art style. The authors trained it on a large curated dataset and benchmarked it on a newly introduced evaluation suite, showing that Step1X-Edit significantly outperforms previous open-source baselines. -
19
VALL-E
PyTorch implementation of VALL-E (Zero-Shot Text-To-Speech)
We introduce a language modeling approach for text to speech synthesis (TTS). Specifically, we train a neural codec language model (called VALL-E) using discrete codes derived from an off-the-shelf neural audio codec model, and regard TTS as a conditional language modeling task rather than continuous signal regression as in previous work. During the pre-training stage, we scale up the TTS training data to 60K hours of English speech which is hundreds of times larger than existing systems. VALL-E emerges in-context learning capabilities and can be used to synthesize high-quality personalized speech with only a 3-second enrolled recording of an unseen speaker as an acoustic prompt. Experiment results show that VALL-E significantly outperforms the state-of-the-art zero-shot TTS system in terms of speech naturalness and speaker similarity. In addition, we find VALL-E could preserve the speaker's emotion and acoustic environment of the acoustic prompt in synthesis. -
20
Anthropic SDK Python
Provides convenient access to the Anthropic REST API from any Python 3
The anthropic-sdk-python repository is the official Python client library for interacting with the Anthropic (Claude) REST API. It is designed to provide a user-friendly, type-safe, and asynchronous/synchronous capable interface for making chat/completion requests to models like Claude. The library includes definitions for all request and response parameters using Python typed objects, automatically handles serialization and deserialization, and wraps HTTP logic (timeouts, retries, error mapping) so that developers can call the API in a clean, high-level way. The SDK supports both synchronous and asynchronous usage (via async/await) depending on context. Importantly, it also supports streaming responses via Server-Sent Events (SSE) so that large outputs can be consumed incrementally rather than waiting for the full response. The client offers helper abstractions for tools (function-style “tools”) and streaming utilities for building interactive agents. -
21
Cactus Needle
26m function call model that runs on incredibly small devices
Needle is an experimental 26-million-parameter function-calling model designed to run on extremely small devices such as phones, watches, glasses, and low-power personal AI hardware. It is based on a Simple Attention Network architecture and was distilled from a much larger model to focus on fast, compact tool-use behavior. The project provides open weights, training details, dataset generation resources, and a playground for testing the model with custom tools. Needle is optimized for single-shot function calling rather than broad conversational ability, so its core use case is selecting the right tool and producing structured arguments. It can be fine-tuned locally, including on consumer machines, which makes it useful for experimentation with small personalized agents. The project is best suited for researchers and developers exploring tiny AI models, edge inference, and lightweight tool-calling systems. -
22
CodeGeeX
CodeGeeX: An Open Multilingual Code Generation Model (KDD 2023)
CodeGeeX is a large-scale multilingual code generation model with 13 billion parameters, trained on 850B tokens across more than 20 programming languages. Developed with MindSpore and later made PyTorch-compatible, it is capable of multilingual code generation, cross-lingual code translation, code completion, summarization, and explanation. It has been benchmarked on HumanEval-X, a multilingual program synthesis benchmark introduced alongside the model, and achieves state-of-the-art performance compared to other open models like InCoder and CodeGen. CodeGeeX also powers IDE plugins for VS Code and JetBrains, offering features like code completion, translation, debugging, and annotation. The model supports Ascend 910 and NVIDIA GPUs, with optimizations like quantization and FasterTransformer acceleration for faster inference. -
23
Core ML Stable Diffusion
Stable Diffusion with Core ML on Apple Silicon
Run Stable Diffusion on Apple Silicon with Core ML. python_coreml_stable_diffusion, a Python package for converting PyTorch models to Core ML format and performing image generation with Hugging Face diffusers in Python. StableDiffusion, a Swift package that developers can add to their Xcode projects as a dependency to deploy image generation capabilities in their apps. The Swift package relies on the Core ML model files generated by python_coreml_stable_diffusion. Hugging Face ran the conversion procedure on the following models and made the Core ML weights publicly available on the Hub. If you would like to convert a version of Stable Diffusion that is not already available on the Hub, please refer to the Converting Models to Core ML. Log in to or register for your Hugging Face account, generate a User Access Token and use this token to set up Hugging Face API access by running huggingface-cli login in a Terminal window. -
24
DeepSeek-OCR
Contexts Optical Compression
DeepSeek-OCR is an open-source optical character recognition solution built as part of the broader DeepSeek AI vision-language ecosystem. It is designed to extract text from images, PDFs, and scanned documents, and integrates with multimodal capabilities that understand layout, context, and visual elements beyond raw character recognition. The system treats OCR not simply as “read the text” but as “understand what the text is doing in the image”—for example distinguishing captions from body text, interpreting tables, or recognizing handwritten versus printed words. It supports local deployment, enabling organizations concerned about privacy or latency to run the pipeline on-premises rather than send sensitive documents to third-party cloud services. The codebase is written in Python with a focus on modularity: you can swap preprocessing, recognition, and post-processing components as needed for custom workflows. -
25
Hunyuan3D-1
A Unified Framework for Text-to-3D and Image-to-3D Generation
Hunyuan3D-1 is an earlier version in the same 3D generation line (the unified framework for text-to-3D and image-to-3D tasks) by Tencent Hunyuan. It provides a framework combining shape generation and texture synthesis, enabling users to create 3D assets from images or text conditions. While less advanced than version 2.1, it laid the foundations for the later PBR, higher resolution, and open-source enhancements. (Note: less detailed public documentation was found for Hunyuan3D-1 compared to 2.1.). Community and ecosystem support (e.g. usage via Blender addon for geometry/texture). Integration into user-friendly tools/platforms.
