Search Results for "learning" - Page 98
Sort By:
Showing 2456 open source projects for "learning"
View related business solutions-
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.
-
$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.
-
1
A free chessprogram based on Fusc# and is written in java. The main idea to rewrite the project in java is to work on new learning and decision strategies.
-
2
-
3
QwQ-32B
QwQ-32B is a reasoning-focused language model for complex tasks
...Built with RoPE positional encoding, SwiGLU activations, RMSNorm, and Attention QKV bias, it excels in multi-turn conversation and long-form reasoning. It supports an extended context length of up to 131,072 tokens and incorporates supervised fine-tuning and reinforcement learning for enhanced instruction-following capabilities. The model is capable of structured thinking and delivers competitive performance against top models like DeepSeek-R1 and o1-mini. Recommended usage involves prompts starting with <think>\n, non-greedy sampling strategies, and support for standardized outputs on math and multiple-choice tasks. ... -
4
Savant
Python Computer Vision & Video Analytics Framework With Batteries Incl
Savant is an open-source, high-level framework for building real-time, streaming, highly efficient multimedia AI applications on the Nvidia stack. It helps to develop dynamic, fault-tolerant inference pipelines that utilize the best Nvidia approaches for data center and edge accelerators. Savant is built on DeepStream and provides a high-level abstraction layer for building inference pipelines. It is designed to be easy to use, flexible, and scalable. It is a great choice for building... -
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.
-
5
LATINO stands for Link analysis and text mining toolbox. It is a software library providing a range of data mining and machine learning algorithms with the emphasis on text mining, link analysis, and data visualization.
-
6
MiniMax-M2.7
Self-evolving AI model for agents, coding, and complex workflows
...With 229B parameters, it introduces a self-evolution framework in which the model actively improves its own capabilities by updating memory, generating skills, and iterating through reinforcement learning experiments. This process enables it to autonomously refine systems, achieving measurable performance gains such as a 30% improvement in programming scaffolds. M2.7 excels in real-world engineering scenarios, including debugging, log analysis, system monitoring, and root cause investigation, demonstrating strong system-level reasoning comparable to SRE workflows. ... -
7
t5-base
Flexible text-to-text transformer model for multilingual NLP tasks
...The model supports multiple languages, including English, French, Romanian, and German. Its flexible architecture and consistent input/output format simplify model reuse and transfer learning across different NLP tasks. T5-base achieves competitive performance across 24 language understanding tasks, as documented in its research paper. -
8
t5-small
T5-Small: Lightweight text-to-text transformer for NLP tasks
...With only 60 million parameters, T5-Small is compact and suitable for fast inference or deployment in constrained environments. It was pretrained on the C4 dataset using both unsupervised denoising and supervised learning on tasks like sentiment analysis, NLI, and QA. Despite its size, it performs competitively across 24 NLP benchmarks, making it a strong candidate for prototyping and fine-tuning. T5-Small is compatible with major deep learning frameworks including PyTorch, TensorFlow, JAX, and ONNX. The model is open-source under the Apache 2.0 license and has wide support across Hugging Face's ecosystem. -
9
This is a very simple implementation of the genetic algorithm framework presented by John Holland, based on Goldberg book Genetic Algorithms in Search, Optimization and Machine Learning.
-
Save Up to 91% on Cloud Compute With Spot VMsRun batch jobs at 60-91% off with Spot VMs. Long-running workloads get automatic discounts with sustained use.
-
10
A Visual Studio .NET C++ application can perform machine learning using genetic algorithm, naive bayes, KNN, and Artificial Neural Networks (ANNs) read and processed from any standard ARFF.
-
11
MiMo-V2.5-Pro
Flagship MoE model for long-context agents and complex coding
...Architecturally, it uses a hybrid attention system combining Sliding Window Attention and Global Attention to significantly reduce memory usage while preserving long-context performance. It also integrates multi-token prediction modules that accelerate inference and improve reinforcement learning efficiency. Trained on around 27 trillion tokens with FP8 mixed precision and refined through supervised fine-tuning, large-scale agentic reinforcement learning, and distillation. -
12
DeepSeek-V3.2-Speciale
High-compute ultra-reasoning model surpassing model surpassing GPT-5
...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. -
13
-
14
Leni is an experimental human language recognition and processing tool which is based on learning and therefore nearly independent on any particular spoken language.
-
15
SLOR stands for "semantic learning object repository" is a software system based on Semantic Web Tecnologies(such as OWL,Protege and Opencyc) which stores educational resources and their metadata(or only the metadata) and provides intelligent searching
-
16
Weka++ is a collection of machine learning and data mining algorithm implementations ported from Weka (http://www.cs.waikato.ac.nz/ml/weka/) from Java to C++, with enhancements for usability as embedded components.
-
17
SuperJabberBot is a project that aims to implements an extendible and very flexible bot for the jabber protocoll in c++.Chatting with the bot you can control a remote server without ssh, and can also be used as a chat bot, learning language from the chat
-
18
A graphical, interactive, multimedia-rich text reader integrated with computer text-to-speech whose level of focus, complexity, and detail is adjustable according to the user's needs. Suitable for users with learning disabilities: i.e. dyslexia.
-
19
litersta
Litersta - textual analytics - software
Unstructured text is no match for Litersta - see further details here: https://litersta.com Working with text now becomes effortless when paired with Litersta textual analytics software. Unlike database fields, which are easily queried, text contains unstructured data that must be parsed for key objects that can be transformed in to powerful metrics. Litersta - textual analytics - software leverages statistical algorithms to programmatically locate, and extract, overall document... -
20
Hy3 preview
Efficient MoE model for reasoning, coding, and AI agent workflows
Hy3 preview is Tencent Hunyuan’s latest open-weight Mixture-of-Experts language model, designed for advanced reasoning, coding, instruction following, and autonomous agent workflows. It is the first model built on Tencent’s rebuilt training infrastructure and introduces significant improvements in context learning, software engineering, and tool-based task execution. The model features 295B total parameters with only 21B activated during inference, plus a dedicated 3.8B Multi-Token Prediction (MTP) layer that accelerates generation through speculative decoding. Architecturally, it uses 192 routed experts with top-8 activation, a dense-MoE hybrid design, and a native 256K-token context window. ... -
21
IntelliView – Big Data Intelligence
AI platform for big data analytics and intelligence investigations
...It helps organizations analyze complex structured and unstructured data, uncover hidden relationships, and transform fragmented information into actionable intelligence. The platform supports big data and machine learning in defence, smart policing, predictive policing, crime analysis, case management for law enforcement, and operational decision-making. With advanced link analysis, entity resolution, pattern detection, and knowledge graph capabilities, IntelliView helps analysts connect people, places, devices, events, transactions, and activities across large datasets. ... -
22
ZAYA1-8B
Efficient MoE reasoning model for coding and math workloads
...It introduces architectural innovations such as Compressed Convolutional Attention, a novel MLP-based expert router, and learned residual scaling to improve routing stability and inference efficiency. The model was trained entirely on AMD infrastructure and refined through supervised fine-tuning and multi-stage reinforcement learning focused on reasoning and coding. -
23
NuMarkdown-8B-Thinking
Reasoning-powered OCR VLM for converting complex documents to Markdown
...Built on Qwen 2.5-VL-7B and fine-tuned with synthetic Doc → Reasoning → Markdown examples, it generates thinking tokens before producing the final Markdown to better handle complex layouts and tables. It uses a two-phase training process: supervised fine-tuning (SFT) followed by reinforcement learning (GRPO) with a layout-centric reward for accuracy on challenging documents. The model excels at non-standard layouts and complex table structures, outperforming non-reasoning OCR systems like GPT-4o and OCRFlux, and competing with large closed-source reasoning models like Gemini 2.5. Thinking token usage can range from 20% to 500% of the final answer, depending on task difficulty. ... -
24
wav2vec2-large-xlsr-53-portuguese
Portuguese ASR model fine-tuned on XLSR-53 for 16kHz audio input
wav2vec2-large-xlsr-53-portuguese is an automatic speech recognition (ASR) model fine-tuned on Portuguese using the Common Voice 6.1 dataset. It is based on Facebook’s wav2vec2-large-xlsr-53, a multilingual self-supervised learning model, and is optimized to transcribe Portuguese speech sampled at 16kHz. The model performs well without a language model, though adding one can improve word error rate (WER) and character error rate (CER). It achieves a WER of 11.3% (or 9.01% with LM) on Common Voice test data, demonstrating high accuracy for a single-language ASR model. ... -
25
DeepSeek-V4-Flash
Efficient MoE model for million-token reasoning and coding
...The model uses a hybrid attention architecture that combines Compressed Sparse Attention and Heavily Compressed Attention to improve long-context efficiency, while Manifold-Constrained Hyper-Connections strengthen signal stability across layers. It is trained on more than 32T tokens and refined through a post-training pipeline that includes supervised fine-tuning, reinforcement learning, domain-specific expert cultivation, and on-policy distillation. DeepSeek-V4-Flash supports non-think, think, and think-max reasoning modes, allowing users to balance speed and depth. It is smaller than DeepSeek-V4-Pro but can approach Pro-level reasoning.