Search Results for "mixture" - Page 2
Sort By:
Showing 49 open source projects for "mixture"
View related business solutions-
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.
-
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.
-
1
Grok-1
Open-source, high-performance Mixture-of-Experts large language model
Grok-1 is a 314-billion-parameter Mixture-of-Experts (MoE) large language model developed by xAI. Designed to optimize computational efficiency, it activates only 25% of its weights for each input token. In March 2024, xAI released Grok-1's model weights and architecture under the Apache 2.0 license, making them openly accessible to developers. The accompanying GitHub repository provides JAX example code for loading and running the model. -
2
Mixtral offloading
Run Mixtral-8x7B models in Colab or consumer desktops
Mixtral-Offloading is an open-source project designed to enable efficient inference of large Mixture-of-Experts language models such as Mixtral-8x7B on hardware with limited GPU memory. The project implements techniques that allow model components to be dynamically moved between CPU memory and GPU memory during inference, significantly reducing the amount of GPU VRAM required to run the model. This approach takes advantage of the sparse activation properties of mixture-of-experts architectures, where only a subset of expert networks are used for each token during generation. ... -
3
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. ... -
4
LLaMA-MoE
Building Mixture-of-Experts from LLaMA with Continual Pre-training
LLaMA-MoE is an open-source project that builds mixture-of-experts language models from LLaMA through expert partitioning and continual pre-training. The repository is centered on making MoE research more accessible by offering smaller and more affordable models with only about 3.0 to 3.5 billion activated parameters, which helps reduce deployment and experimentation costs. Its architecture works by splitting LLaMA feed-forward networks into sparse experts and adding gating mechanisms so that only selected experts are activated during inference and training. ... -
$300 in Free Credit Towards Top Cloud ServicesStart your project in minutes. After credits run out, 20+ products include free monthly usage. Only pay when you're ready to scale.
-
5
QuantResearch
Quantitative analysis, strategies and backtests
...These include implementations of factor models, statistical arbitrage strategies, portfolio optimization methods, and reinforcement learning approaches to trading. The repository also explores financial modeling topics such as vector autoregression, Gaussian mixture models, and option pricing techniques. Many notebooks demonstrate backtesting pipelines that allow users to evaluate trading strategies using historical market data. The project integrates machine learning methods with traditional quantitative finance models, illustrating how statistical techniques can be applied to asset management and trading. -
6
MLPACK is a C++ machine learning library with emphasis on scalability, speed, and ease-of-use. Its aim is to make machine learning possible for novice users by means of a simple, consistent API, while simultaneously exploiting C++ language features to provide maximum performance and flexibility for expert users. * More info + downloads: https://mlpack.org * Git repo: https://github.com/mlpack/mlpack
-
7
Twinify
Privacy-preserving generation of a synthetic twin to a data set
twinify is a software package for the privacy-preserving generation of a synthetic twin to a given sensitive tabular data set. On a high level, twinify follows the differentially private data-sharing process introduced by Jälkö et al.. Depending on the nature of your data, twinify implements either the NAPSU-MQ approach described by Räisä et al. or finds an approximate parameter posterior for any probabilistic model you formulated using differentially private variational inference (DPVI).... -
8
Scripting Language Bindings
A port of WFOPT to the several scripting languages
This project contains bindings for various scripting languages to the Wheefun Options Parsing Library. It is meant to provide parity with the C implementation so .NET languages can take advantage of WFOPT. For more information, please see the main page. -
9
L5RCM
GM tool for the RPG game "Legend of the Five Rings" 4th edition
...It can be used to create PC and NPC and to manage characters during playtime. The Legend of the Five Rings RPG is a role playing game that takes place in Rokugan, a mixture of Asian medieval culture. You can find more on L5R RPG on its official site. -
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
10
SVoice (Speech Voice Separation)
We provide a PyTorch implementation of the paper Voice Separation
...The model employs gated neural networks with recurrent processing blocks that disentangle voices over multiple computational steps, while maintaining speaker consistency across output channels. Separate models are trained for different speaker counts, and the largest-capacity model dynamically determines the actual number of speakers in a mixture. The repository includes all necessary scripts for training, dataset preparation, distributed training, evaluation, and audio separation. -
11
Polluted gases Estimator
Create, estimate and analyses gas pollutants and the possible costs
The SPS machines are not designed to filter the particulates to be of acceptable size, level or concentration, unlike Wet Scrubbers, Electrostatic Precipitators, Diesel Particulate Filter DPF etc. The reality is that finest and ultra-finest Particulates tends to behave like gas rather than a gas-solids mixture or simply can be transported by vapour. Is the reason why many filtering technologies are ineffective. However, SPS technology is post-combustion system or last stage of production, which results in packaged CO2 or any other gases, without worrying about gas dilution and intrusion processes which more complicated and costly also are not well investigated, that is a setback for many CO2 technology. ... -
12
Mixture100
Simply percent calculator
For making various mixtures, like homemade alcohol, brine or e-liquids. Add a components, set a percentage in total, set how much I want a given mixture and save, share or print recipe. -
13
fitGCP
Fitting genome coverage distributions with mixture models
...fitGCP is a framework for fitting mixtures of probability distributions to genome coverage profiles. Besides commonly used distributions, fitGCP uses distributions tailored to account for common artifacts. The mixture models are iteratively fitted based on the Expectation-Maximization algorithm. Please find the accompanying paper here: http://dx.doi.org/10.1093/bioinformatics/btt147 -
14
de:Code
Top-down dungeon crawler
de:Code is a 3rd-person top-down dungeon crawler. The world is procedurally generated using the file structure of the users hard drive. The game will use a mixture of different genres including steampunk, fantasy, mid-evil, and modern. The user will have to travel down 4 main paths each progressively harder than the last and each will have more than one genre conflicting inside. Each main path (connected by a central hub) will get harder as the user progresses down, finally reaching a unique boss at the end. -
15
GalGen Trader
A 2D Elite-style game written in Python 3.2.
...This functionality is supported by the game being written in Python 3, with its powerful support for including external code at run-time. The graphics will be a simple mixture of 2D raster and vector imagery with text-based menus, and the music will be highly reminiscent of the 80's 'chiptunes' that made up the soundtracks for games on the Amiga and Commodore 64. -
16
This project hosts tools used for analysis of Gaussian Mixture Distributions (GMDs) which are used for statistical signal processing. The tools are libraries for implementing GMD operations and programs used to analyze properties of GMDs.
-
17
kiki the nanobot is a 3-D puzzle game. It is basically a mixture of the games Sokoban and Kula-World.
-
18
mod_npy is alternative way of running Python scripts under Apache - alternative to having mod_python installed, or running as CGI. It allows mixing Python code with HTML much like PHP. It's a mixture of Python power and PHP style page writing.
-
19
This project aims at writing a threaded, object-oriented and scriptable game engine targetting the .NET platform, using a mixture of c# or managed c++ ports of famous c/c++ components such as OGRE, CEGUI, Newton, Lua, Python, Audiere, OpenAL, etc...
-
20
clusterviz allows to cluster three-dimensional data. The clustering process is visualized using OpenGL. As clustering algorithms the family of k-means algorithms is implemented, including mixture models.
-
21
Mistral Small 4
Model that fuses instruct, reasoning and agentic skills
...These models are part of the broader Mistral Small family, which is designed to deliver strong performance across a wide range of everyday AI tasks while maintaining relatively low latency and efficient deployment requirements. The collection reflects an evolution toward hybrid mixture-of-experts architectures that dynamically activate subsets of parameters during inference, allowing large models to remain computationally efficient. Mistral Small 4 models are built to handle tasks such as conversational AI, software development assistance, and reasoning-heavy problem solving, making them versatile tools for both developers and enterprise applications. -
22
Nemotron 3 Nano
LL model providing reasoning and conversational capabilities
...It is trained from scratch and built using a hybrid architecture that integrates Transformer attention layers with Mamba-style sequence modeling components inside a Mixture-of-Experts framework. This architecture allows the system to maintain strong reasoning capabilities while improving throughput and reducing the computational cost associated with large context processing. The model is designed as a general-purpose language system capable of handling tasks such as chat interaction, coding assistance, document analysis, and instruction following. -
23
Nemotron 3 Super
Open language model developed by NVIDIA as part of Nemotron-3 family
NVIDIA-Nemotron-3-Super-120B-A12B-FP8 is a large-scale open language model developed by NVIDIA as part of the Nemotron-3 family of generative AI systems designed for advanced reasoning, conversational interaction, and agent-based workflows. The model contains approximately 120 billion parameters, but employs a Mixture-of-Experts architecture that activates only a smaller subset of parameters during inference, improving computational efficiency while maintaining high capability. Its architecture combines Transformer attention layers with Mamba state-space components to balance long-context reasoning, memory efficiency, and high-quality language generation. ... -
24
Leanstral
Open-source code agent designed for Lean 4
...By focusing on theorem proving and formal reasoning, Leanstral represents a specialized direction within large language models, targeting domains that require strict correctness and logical rigor rather than general conversational tasks. It leverages modern large-scale architectures, likely incorporating mixture-of-experts techniques, to balance efficiency and capability while handling structured symbolic reasoning tasks. The model can assist in writing proofs, exploring mathematical structures, and validating logical properties in code.
