Search Results for "memory" - Page 9
Sort By:
Showing 248 open source projects for "memory"
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.
-
Auth0 B2B Essentials: SSO, MFA, and RBAC Built InAuth0's B2B Essentials plan gives you everything you need to ship secure multi-tenant apps. Unlimited orgs, enterprise SSO, RBAC, audit log streaming, and higher auth and API limits included. Add on M2M tokens, enterprise MFA, or additional SSO connections as you scale.
-
1
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. ... -
2
Ailice
AIlice is a fully autonomous, general-purpose AI agent
AIlice is an open-source autonomous AI agent framework built to function as a general-purpose assistant that can plan, decompose, and execute complex tasks through a structured multi-agent architecture. The project presents itself as a standalone assistant powered by open-source language models, with an internal design that treats user requests almost like executable programs rather than simple chat prompts. Its core IACT architecture allows the system to break large goals into smaller... -
3
AI-Aimbot
CS2, Valorant, Fortnite, APEX, every game
...The project emphasizes that it is intended for educational purposes to illustrate potential vulnerabilities in game design and anti-cheat systems. Because the system relies solely on visual detection rather than reading game memory, it attempts to bypass certain traditional anti-cheat detection methods. -
4
Punica
Serving multiple LoRA finetuned LLM as one
...LoRA is a parameter-efficient fine-tuning method that allows developers to adapt large pretrained models to specific tasks by adding lightweight adapter layers rather than retraining the entire model. Punica introduces a serving architecture that allows multiple LoRA adapters to share the same base model during inference, significantly reducing memory consumption and computational overhead. The system includes specialized CUDA kernels that enable batched GPU operations across different LoRA models simultaneously. This design allows a single GPU cluster to host many task-specific models while maintaining high throughput and minimal latency. The architecture also includes scheduling mechanisms that coordinate requests from multiple tenants and distribute workloads efficiently across available resources. -
Atera - an All-in-one platform for IT managementYour IT essentials, integrated & elevated. Take your IT management from automated to autonomous, download Atera's agent to start your free trial!
-
5
GPT Discord Bot
Example Discord bot written in Python that uses the completions API
GPT Discord Bot is an example project from OpenAI that shows how to integrate the OpenAI API with Discord using Python. The bot uses the Chat Completions API (defaulting to gpt-3.5-turbo) to carry out conversational interactions and the Moderations API to filter user messages. It is built on top of the discord.py framework and the OpenAI Python library, providing a simple, extensible template for building AI-powered Discord applications. The bot supports a /chat command that spawns a public... -
6
SuperAGI
A dev-first open source autonomous AI agent framework
...Get insights into your agent’s performance and optimize accordingly. Control token usage to manage costs effectively. Enable your agents to learn and adapt by storing their memory. Get notified when agents get stuck in the loop, and provide proactive resolution. Read and store files generated by Agents. -
7
Firefly LLM
A large model training tool that supports training large models
Firefly is an open-source framework designed to simplify the training and fine-tuning of large language models through a unified and configurable workflow. The project provides a comprehensive environment where developers can perform tasks such as model pre-training, instruction tuning, and preference optimization using widely adopted machine learning techniques. Its architecture supports both full-parameter training and parameter-efficient strategies like LoRA and QLoRA, making it suitable... -
8
RWKV
RNN with great LLM performance
...The project is built around the idea that a model can be trained in a parallelizable way like a GPT-style transformer while running inference with recurrent efficiency. This gives RWKV important advantages for long-context use, including lower memory pressure and no traditional key-value cache requirement. The repository includes training code, model notes, research material, and references to current RWKV weights. Its main value is providing the foundation for experimenting with efficient large language models that combine transformer-like scalability with RNN-like runtime behavior. -
9
xTuring
Easily build, customize and control your own LLMs
xTuring is an open-source AI personalization software. xTuring makes it easy to build and control LLMs by providing a simple interface to personalize LLMs to your own data and application. xTuring provides fast, efficient and simple fine-tuning of LLMs, such as LLaMA, GPT-J, Galactica, and more. By providing an easy-to-use interface for fine-tuning LLMs to your own data and application, xTuring makes it simple to build, customize and control LLMs. The entire process can be done inside your... -
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
FastViT
This repository contains the official implementation of research
...The codebase provides reference implementations and checkpoints that make it easy to evaluate or fine-tune on downstream datasets. In practice, FastViT offers drop-in backbones that reduce compute and memory pressure without exotic training tricks. -
11
Language Models
Explore large language models in 512MB of RAM
...By using small and optimized models, the library allows LLM inference to run in environments with limited resources, sometimes requiring only a few hundred megabytes of memory. The package provides simple APIs that allow developers to generate text, perform semantic search, classify text, and answer questions using local models. It is particularly useful for educational purposes, as it demonstrates the fundamental mechanics of language model inference and prompt-based applications. The repository includes multiple example applications such as chatbots, document question answering systems, and information retrieval tools. -
12
Metaseq
Repo for external large-scale work
Metaseq is a flexible, high-performance framework for training and serving large-scale sequence models, such as language models, translation systems, and instruction-tuned LLMs. Built on top of PyTorch, it provides distributed training, model sharding, mixed-precision computation, and memory-efficient checkpointing to support models with hundreds of billions of parameters. The framework was used internally at Meta to train models like OPT (Open Pre-trained Transformer) and serves as a reference implementation for scaling transformer architectures efficiently across GPUs and nodes. It supports both pretraining and fine-tuning workflows with data pipelines for text, multilingual corpora, and custom tokenization schemes. ... -
13
ToMe (Token Merging)
A method to increase the speed and lower the memory footprint
ToMe (Token Merging) is a PyTorch-based optimization framework designed to significantly accelerate Vision Transformer (ViT) architectures without retraining. Developed by researchers at Facebook (Meta AI), ToMe introduces an efficient technique that merges similar tokens within transformer layers, reducing redundant computation while preserving model accuracy. This approach differs from token pruning, which removes background tokens entirely; instead, ToMe merges tokens based on feature... -
14
NanoDet-Plus
Lightweight anchor-free object detection model
Super fast and high accuracy lightweight anchor-free object detection model. Real-time on mobile devices. NanoDet is a FCOS-style one-stage anchor-free object detection model which using Generalized Focal Loss as classification and regression loss. In NanoDet-Plus, we propose a novel label assignment strategy with a simple assign guidance module (AGM) and a dynamic soft label assigner (DSLA) to solve the optimal label assignment problem in lightweight model training. We also introduce a... -
15
Amiga Memories
A walk along memory lane
Amiga Memories is a project (started & released in 2013) that aims to make video programmes that can be published on the internet. The images and sound produced by Amiga Memories are 100% automatically generated. The generator itself is implemented in Squirrel, the 3D rendering is done on GameStart 3D. An Amiga Memories video is mostly based on a narrative. The purpose of the script is to define the spoken and written content. The spoken text will be read by a voice synthesizer (Text To... -
16
Mars Framework
Mars is a tensor-based unified framework for large-scale data
...Its architecture automatically divides large computational tasks into smaller chunks that can be executed across multiple nodes in a cluster, allowing complex analytics, machine learning workflows, and data transformations to run efficiently at scale. Mars is particularly useful for workloads that exceed the memory capacity of a single machine or require high levels of parallel processing. -
17
OpenDelta
A plug-and-play library for parameter-efficient-tuning
OpenDelta is an open-source parameter-efficient fine-tuning library that enables efficient adaptation of large-scale pre-trained models using delta tuning techniques. OpenDelta is a toolkit for parameter-efficient tuning methods (we dub it as delta tuning), by which users could flexibly assign (or add) a small amount parameters to update while keeping the most parameters frozen. By using OpenDelta, users could easily implement prefix-tuning, adapters, Lora, or any other types of delta tuning... -
18
LSTMs for Human Activity Recognition
Human Activity Recognition example using TensorFlow on smartphone
LSTM-Human-Activity-Recognition is a machine learning project that demonstrates how recurrent neural networks can be used to recognize human activities from sensor data. The repository implements a deep learning model based on Long Short-Term Memory (LSTM) networks to classify physical activities using time-series data collected from wearable sensors. The project uses the well-known Human Activity Recognition dataset derived from smartphone accelerometer and gyroscope signals. Through the use of sequential neural network architectures, the system learns patterns in motion data that correspond to activities such as walking, sitting, standing, or climbing stairs. ... -
19
KoboldAI
Your gateway to GPT writing
This is a browser-based front-end for AI-assisted writing with multiple local & remote AI models. It offers the standard array of tools, including Memory, Author's Note, World Info, Save & Load, adjustable AI settings, formatting options, and the ability to import existing AI Dungeon adventures. You can also turn on Adventure mode and play the game like AI Dungeon Unleashed. Stories can be played like a Novel, a text adventure game or used as a chatbot with an easy toggles to change between the multiple gameplay styles. ... -
20
Apple Neural Engine (ANE) Transformers
Reference implementation of the Transformer architecture optimized
ANE Transformers is a reference PyTorch implementation of Transformer components optimized for Apple Neural Engine on devices with A14 or newer and on Macs with M1 or newer chips. It demonstrates how to structure attention and related layers to achieve substantial speedups and lower peak memory compared to baseline implementations when deployed to ANE. The repository targets practitioners who want to keep familiar PyTorch modeling while preparing models for Core ML/ANE execution paths. Documentation highlights reported improvements in throughput and memory residency, while releases track incremental fixes and packaging updates. ... -
21
min(DALL·E)
min(DALL·E) is a fast, minimal port of DALL·E Mini to PyTorch
...The only third-party dependencies are numpy, requests, pillow and torch. The required models will be downloaded to models_root if they are not already there. Set the dtype to torch.float16 to save GPU memory. If you have an Ampere architecture GPU you can use torch.bfloat16. Set the device to either cuda or "cpu". Once everything has finished initializing, call generate_image with some text as many times as you want. Use a positive seed for reproducible results. Higher values for supercondition_factor result in better agreement with the text but a narrower variety of generated images. ... -
22
Fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python
Fairseq(-py) is a sequence modeling toolkit that allows researchers and developers to train custom models for translation, summarization, language modeling and other text generation tasks. We provide reference implementations of various sequence modeling papers. Recent work by Microsoft and Google has shown that data parallel training can be made significantly more efficient by sharding the model parameters and optimizer state across data parallel workers. These ideas are encapsulated in the... -
23
Apache MXNet (incubating)
A flexible and efficient library for deep learning
Apache MXNet is an open source deep learning framework designed for efficient and flexible research prototyping and production. It contains a dynamic dependency scheduler that automatically parallelizes both symbolic and imperative operations. On top of this is a graph optimization layer, overall making MXNet highly efficient yet still portable, lightweight and scalable. -
24
NWT - Pytorch (wip)
Implementation of NWT, audio-to-video generation, in Pytorch
Implementation of NWT, audio-to-video generation, in Pytorch. The paper proposes a new discrete latent representation named Memcodes, which can be succinctly described as a type of multi-head hard-attention to learned memory (codebook) key/values. They claim the need for less codes and smaller codebook dimensions in order to achieve better reconstructions. -
25
Voice Cloning App
A Python/Pytorch app for easily synthesising human voices
...You'll then need to download the model.pbmm and alphabet.txt files for your language. Requires Windows 10 or Ubuntu 20.04+ operating system, 5GB+ Disk space, and NVIDIA GPU with at least 4GB of memory & driver version 456.38+ (optional). Automatic dataset generation (with support for subtitles and audiobooks) Additional language support. Local & remote training. Easy train start/stop. Data importing/exporting.
