Search Results for "artificial intelligence java source code" - Page 77
Sort By:
Showing 1930 open source projects for "artificial intelligence java source code"
View related business solutions-
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
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.
-
1
A gui based man against machine poker (texas hold them) end user application which will deduce and adapt to the player's strategy.
-
2
EveAI processes the data assuming that it has already been read by a sensor. Theoretically this should give it reflex behavior. Now the end product should be a self conscious machine future plans are to include the field of robotics.
-
3
Ztooly
Ztooly is a comprehensive collection of 50+ free online tools designed
Ztooly is a comprehensive collection of 50+ free online tools designed to boost productivity and simplify everyday tasks. From AI-powered generators to image editing, data conversion, PDF handling, social tools, and more — Ztooly is your all-in-one web toolkit. -
4
This project represents online shop for books. The thing that will make this web application better than the others will be the artificial intelligence that will contain
-
Turn Your Content into Interactive Magic - For FreeTransform anything you share into an engaging digital experience - for free. Instantly convert your PDFs, slides, and files into dynamic, interactive sessions with built-in collaboration tools, activities, and real-time assessment. From teaching to training to team building, make every presentation unforgettable. Used by millions for education, business, and professional development.
-
5
This project is intended to become an advanced software tool which will allocate resources for projects described by Gantt charts and rules, it also will try to create plans and schedules, based on templates, rules and historical information.
-
6
Multilayer neural network sudoku generator that can be trained to produce puzzles with different degree of dificulty and imitate those made by people.
-
7
SmolLM3
Multilingual 3B LLM optimized for reasoning, math, and long contexts
SmolLM3 is a 3.08B parameter decoder-only language model designed by Hugging Face to deliver high performance in reasoning, math, and multilingual understanding. Trained on 11.2T tokens with a curriculum of web, code, and mathematical data, it uses advanced features like GQA and NoPE. The model supports extended context lengths up to 128k tokens via YaRN extrapolation, making it highly suitable for long-context applications. It outperforms or rivals larger models like Qwen3 and LLaMA3... -
8
DeepSeek-V3-0324
Advanced multilingual LLM with enhanced reasoning and code generation
DeepSeek-V3-0324 is a powerful large language model by DeepSeek AI that significantly enhances performance over its predecessor, especially in reasoning, programming, and Chinese language tasks. It achieves major benchmark improvements, such as +5.3 on MMLU-Pro and +19.8 on AIME, and delivers more executable, aesthetically improved front-end code. Its Chinese writing and search-answering capabilities have also been refined, generating more fluent, contextually aware long-form outputs. Key... -
9
Generic engine to filter information. We wish to show that the power of expression of a filter makes it possible to appreciably reduce the size of the code necessary to extract information and that it is possible in Python.
-
Crowdtesting That Delivers | TesteumTesteum connects your software, app, or website to a worldwide network of testers, delivering detailed feedback in under 48 hours. Ensure functionality and refine UX on real devices, all at a fraction of traditional costs. Trusted by startups and enterprises alike, our platform streamlines quality assurance with actionable insights.
-
10
-
11
This projects implements various optimization heuristics and meta-heuristics (such as local search, VND, GRASP, Simulated Annealing, and more still to come) finding solutions on the post enrolment course timetabling problem.
-
12
Interlogy - next generation knowledge storage and prezentation system. Gives wide functionality for knwoledge evaluation. Interlogy is the same as forum, wiki, chat, socialnetwork, but all together.
-
13
Top Engine the Semantic Web Engine for the Enterprise. Top Engine is a Business Rule Engine that utilize OWL DL ontologies for vocabulary primitive to write rules on top of ontology. Top Engine support forward and backward chaining with truth maintenance
-
14
GraphSpider is a pattern matcher which searches parsed text in phrase-structure tree or dependency graph format for syntactic structures matching a set of patterns in MPL, a regexp-like pattern language. Applications: information extraction, text mining.
-
15
Devstral
Agentic 24B LLM optimized for coding tasks with 128k context support
Devstral-Small-2505 is a 23.6B parameter language model fine-tuned by Mistral AI and All Hands AI, built specifically for agentic software engineering tasks. Based on Mistral-Small-3.1, it supports a 128k context window and excels in exploring codebases, editing multiple files, and tool usage. The model achieves state-of-the-art open-source performance on SWE-Bench Verified with a score of 46.8%, surpassing much larger models. Devstral is designed for local and production-level deployments... -
16
Meta-Llama-3-8B
Versatile 8B language model optimized for helpful, safe dialogue
...-following, reasoning, and code generation. It significantly outperforms previous Llama 2 models and many open-source alternatives on benchmarks like MMLU, GSM8K, and HumanEval. Designed with safety in mind, Llama 3 includes alignment via supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF), and is backed by tools like Llama Guard 2 and Code Shield. The model is intended for commercial and research use, especially for building assistant-like chatbots. -
17
gemma-7b
Compact, state-of-the-art LLM by Google for text generation tasks
Gemma-7B is a lightweight, open-source, decoder-only language model developed by Google, built using the same research and technology behind the Gemini family. With 8.5 billion parameters and an 8192-token context window, it is optimized for English text generation tasks like question answering, summarization, reasoning, and creative writing. Trained on 6 trillion tokens including web documents, code, and mathematical texts, Gemma-7B provides competitive performance across a wide range of NLP... -
18
Solve Logic Word Puzzles with CLP
Constraint Logic can solve word logic puzzles.
Learn basic constraint logic programming by solving logic word puzzles. Go to http://eclipse.dougedmunds.com . This tutorial will show you how to solve easy 1 star to hard 5 star puzzles, using the eCLiPSe-CLP language (available at http://eclipseclp.org/). Don't confuse this programming language (a prolog language) with the IDE for Java. -
19
OpenVLA 7B
Vision-language-action model for robot control via images and text
... supports real-world robotics tasks, with robust generalization to environments seen in pretraining. Its actions include delta values for position, orientation, and gripper status, and can be un-normalized based on robot-specific statistics. OpenVLA is MIT-licensed, fully open-source, and designed collaboratively by Stanford, Berkeley, Google DeepMind, and TRI. Deployment is facilitated via Python and Hugging Face tools, with flash attention support for efficient inference. -
20
The OBO-Annotator is a semantic NLP tool that is designed to give its end-users a great deal of flexibility to combine any number of OBO ontologies from the OBO foundry regardless of their format and use them to annotate text-bases.
-
21
DeepSWE-Preview
State-of-the-art RL-trained coding agent for complex SWE tasks
DeepSWE-Preview is a 32.8B parameter open-source coding agent trained solely with reinforcement learning (RL) to perform complex software engineering (SWE) tasks. Built on top of Qwen3-32B, it achieves 59% accuracy on the SWE-Bench-Verified benchmark—currently the highest among open-weight models. The model navigates and edits large codebases using tools like a file editor, bash execution, and search, within the R2E-Gym environment. Its training emphasizes sparse reward signals, test-time... -
22
wav2vec2-large-xlsr-53-portuguese
Portuguese ASR model fine-tuned on XLSR-53 for 16kHz audio input
... Voice test data, demonstrating high accuracy for a single-language ASR model. Inference can be done using HuggingSound or via a custom PyTorch script using Hugging Face Transformers and Librosa. Training scripts and evaluation methods are open source and available on GitHub. It is released under the Apache 2.0 license and intended for ASR tasks in Brazilian Portuguese. -
23
FLUX.1-schnell
12B-parameter image generator using fast rectified flow transformers
FLUX.1-schnell is a 12 billion parameter text-to-image model developed by Black Forest Labs, designed for high-quality image generation using rectified flow transformers. It produces competitive visual results with strong prompt adherence, rivaling closed-source models in just 1 to 4 inference steps. Trained using latent adversarial diffusion distillation, the model is optimized for both quality and speed. It is released under the Apache 2.0 license, allowing commercial, scientific... -
24
Mistral-7B-v0.1
Efficient 7B parameter LLM outperforming Llama 2 13B in benchmarks
Mistral-7B-v0.1 is a pretrained 7-billion parameter transformer language model developed by Mistral AI, designed to deliver high performance with optimized compute efficiency. It outperforms Llama 2 13B on all evaluated benchmarks despite its smaller size. The architecture integrates Grouped-Query Attention (GQA) and Sliding-Window Attention, enabling efficient inference and improved long-context performance. Mistral-7B uses a byte-fallback BPE tokenizer for better multilingual and code... -
25
A software framework to support distributed evolutionary software development. It dynamically creates a network of nodes that can run a pre-distributed source code (e.g. artificial lifeforms). The results of the calculation will be sent back to the maste
