Search Results for "mathematical" - Page 2
Sort By:
Showing 44 open source projects for "mathematical"
View related business solutions-
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
Stop Cyber Threats with VM-Series Next-Gen Firewall on AzureGain integrated visibility across all traffic in a single pass. Deploy Palo Alto Networks VM-Series to determine application identity and content while automating security policy updates via rich APIs.
-
1
HunyuanOCR
OCR expert VLM powered by Hunyuan's native multimodal architecture
...Despite being fairly lightweight (about 1 billion parameters), it delivers state-of-the-art performance across a wide variety of OCR tasks, outperforming many traditional OCR systems and even other multimodal models on benchmark suites. HunyuanOCR handles complex documents: multi-column layouts, tables, mathematical formulas, mixed languages, handwritten or stylized fonts, receipts, tickets, and even video-frame subtitles. The project provides code, pretrained weights, and inference instructions, making it feasible to deploy locally or on a server, and to integrate with applications. -
2
DeepSeek Math
Pushing the Limits of Mathematical Reasoning in Open Language Models
DeepSeek-Math is DeepSeek’s specialized model (or dataset + evaluation) focusing on mathematical reasoning, symbolic manipulation, proof steps, and advanced quantitative problem solving. The repository is likely to include fine-tuning routines or task datasets (e.g. MATH, GSM8K, ARB), demonstration notebooks, prompt templates, and evaluation results on math benchmarks. The goal is to push DeepSeek’s performance in domains that require rigorous symbolic steps, calculus, linear algebra, number theory, or multi-step derivations. ... -
3
Qwen2.5-Coder
Qwen2.5-Coder is the code version of Qwen2.5, the large language model
...It includes multiple model sizes—ranging from 0.5B to 32B parameters—providing solutions for a wide array of coding needs. The model supports over 92 programming languages and offers exceptional performance in generating code, debugging, and mathematical problem-solving. Qwen2.5-Coder, with its long context length of 128K tokens, is ideal for a variety of use cases, from simple code assistants to complex programming scenarios, matching the capabilities of models like GPT-4o. -
4
GLM-4-32B-0414
Open Multilingual Multimodal Chat LMs
...The model is pre-trained on 15 trillion tokens of high-quality data, including substantial synthetic reasoning datasets, and further enhanced with reinforcement learning and human preference alignment for improved instruction-following and function calling. Variants like GLM-Z1-32B-0414 offer deep reasoning and advanced mathematical problem-solving, while GLM-Z1-Rumination-32B-0414 specializes in long-form, complex research-style writing using scaled reinforcement learning and external search tools. Despite its large capacity, the model supports user-friendly local deployment and efficient fine-tuning with available scripts. -
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
5
ToRA
Tool-integrated Reasoning LLM Agents
...The framework was designed to address known weaknesses of large language models in mathematical problem solving and formal reasoning tasks. Training data includes tool-use trajectories that teach the model when to reason verbally and when to delegate tasks to specialized tools. -
6
snorkel
A system for quickly generating training data with weak supervision
...The Snorkel project started at Stanford in 2016 with a simple technical bet: that it would increasingly be the training data, not the models, algorithms, or infrastructure, that decided whether a machine learning project succeeded or failed. Given this premise, we set out to explore the radical idea that you could bring mathematical and systems structure to the messy and often entirely manual process of training data creation and management, starting by empowering users to programmatically label, build, and manage training data. Snorkel Flow, an end-to-end machine learning platform for developing and deploying AI applications. Snorkel Flow incorporates many of the concepts of the Snorkel project with a range of newer techniques around weak supervision modeling, data augmentation, multi-task learning, data slicing and structuring. -
7
Alpaca-CoT
We unified the interfaces of instruction-tuning data
Alpaca-CoT is an open research project focused on improving reasoning capabilities in language models through chain-of-thought training data. The project builds upon the Alpaca instruction-tuning approach by introducing datasets and methods that encourage models to produce intermediate reasoning steps when solving problems. Instead of generating answers directly, the model learns to produce logical reasoning sequences that lead to the final solution. This chain-of-thought supervision helps... -
8
picoGPT
An unnecessarily tiny implementation of GPT-2 in NumPy
...It allows users to understand how tokenization, transformer layers, attention mechanisms, and autoregressive text generation operate in modern large language models. The project uses a small amount of code to illustrate the essential mathematical operations involved in training and running a transformer-based neural network. Because the code is intentionally lightweight, it is often used as a teaching resource for students learning about natural language processing and deep learning architectures. Developers can explore the repository to understand how language models generate text and how transformer components interact within the architecture. -
9
Machine Learning Glossary
Machine learning glossary
...It covers a wide range of topics including neural networks, regression models, optimization techniques, loss functions, and evaluation metrics. The content is organized into sections that progressively introduce key ideas from basic machine learning concepts to more advanced mathematical topics. Many pages include diagrams or code examples to illustrate how algorithms work in practice. Because the project emphasizes accessibility, it is particularly useful for beginners who want a conceptual overview of machine learning terminology before diving into more technical research papers. -
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.
-
10
Grade School Math
8.5K high quality grade school math problems
The grade-school-math repository (sometimes called GSM8K) is a curated dataset of 8,500 high-quality grade school math word problems intended for evaluating mathematical reasoning capabilities of language models. It is structured into 7,500 training problems and 1,000 test problems. These aren’t trivial exercises — many require multi-step reasoning, combining arithmetic operations, and handling intermediate steps (e.g. “If she sold half as many in May… how many in total?”). The problems are written by human authors (not automatically generated) to ensure linguistic variety and realism. ... -
11
DeepLearning
Deep Learning (Flower Book) mathematical derivation
" Deep Learning " is the only comprehensive book in the field of deep learning. The full name is also called the Deep Learning AI Bible (Deep Learning) . It is edited by three world-renowned experts, Ian Goodfellow, Yoshua Bengio, and Aaron Courville. Includes linear algebra, probability theory, information theory, numerical optimization, and related content in machine learning. At the same time, it also introduces deep learning techniques used by practitioners in the industry, including... -
12
Deep-Learning-with-PyTorch-Tutorials
Deep Learning and PyTorch Introduction Video Tutorial with Source Code
...It provides source code, notebooks, and presentation materials for a practical video-based learning path. The lessons begin with PyTorch setup, tensors, indexing, mathematical operations, gradients, and basic optimization. They then move into neural networks, logistic regression, multilayer perceptrons, CNNs, ResNet, RNNs, LSTMs, autoencoders, VAEs, GANs, graph convolutional networks, and transfer learning. The repository is designed for learners who want to connect deep learning concepts with executable examples. ... -
13
Machine Learning From Scratch
Bare bones NumPy implementations of machine learning models
ML-From-Scratch is an open-source machine learning project that demonstrates how to implement common machine learning algorithms using only basic Python and NumPy rather than relying on high-level frameworks. The goal of the project is to help learners understand how machine learning algorithms work internally by building them step by step from fundamental mathematical operations. The repository includes implementations of algorithms ranging from simple models such as linear regression and logistic regression to more complex techniques such as decision trees, support vector machines, clustering methods, and neural networks. Because the code avoids external machine learning libraries, it exposes the full logic behind model training, optimization, and prediction processes. ... -
14
Lihang
Statistical learning methods (2nd edition) [Li Hang]
...In addition to code examples, the project contains supplementary materials such as formula references, glossaries of technical terms, and documentation explaining mathematical notation used throughout the algorithms. The repository also provides links to related research papers and references that expand on the theoretical background presented in the book. -
15
Virtual Laboratory Environment
A multi-modeling and simulation environment to study complex systems
...VLE provides a complete set of C++ libraries, called VFL (VLE Foundation Libraries), to develop DEVS models, to gets results of simulations, to launch simulation on cluster. The models can be developed with the DEVS formalism or with the classical mathematical formalism: Ordinary Differential Equation with Euler, Range-Kutta or QSS integrator, Finite state automaton (FDDEVS, UML State chart, Hybrid Petri net). The VLE environment provides an IDE to develop C++ models, DEVS coupled models. VLE have also three ports to use the VFL with Python, Java and R programming languages. -
16
TalkMaths is a speech user interface that extends the speech recognition program Dragon NaturallySpeaking by parsing spoken mathematical expressions into MathML and/or LaTeX. TalkMaths allows the user to create documents in MathML or LaTeX hands-free.
-
17
Leanstral
Open-source code agent designed for Lean 4
...The model can assist in writing proofs, exploring mathematical structures, and validating logical properties in code. -
18
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. ... -
19
DeepSeek-V3.2
High-efficiency reasoning and agentic intelligence model
...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.
