Search Results for "base" - Page 7
Sort By:
Showing 321 open source projects for "base"
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.
-
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.
-
1
CodeLlama
Inference code for CodeLlama models
Code Llama is a family of Llama-based code models optimized for programming tasks such as code generation, completion, and repair, with variants specialized for base coding, Python, and instruction following. The repo documents the sizes and capabilities (e.g., 7B, 13B, 34B) and highlights features like infilling and large input context to support real IDE workflows. It targets both general software synthesis and language-specific productivity, offering strong performance among open models at release time. ... -
2
Chinese-LLaMA-Alpaca-3
Chinese Llama-3 LLMs) developed from Meta Llama 3
...It extends the original LLaMA models with expanded Chinese vocabularies and additional pretraining on Chinese corpora to improve semantic encoding and decoding specifically for Chinese text. Alongside the base models, the project also releases Chinese Alpaca models that are fine-tuned on instruction datasets so they behave more like conversational and instruction-following AI assistants. It includes scripts and tooling that let researchers or developers run training, fine-tuning, quantization, and deployment on local machines (CPU or GPU), making experimentation and testing accessible without requiring large clusters. -
3
ComfyUI InstantID ZHO
Unofficial implementation of InstantID for ComfyUI
ComfyUI-InstantID is an unofficial ComfyUI implementation of InstantID for identity-preserving image generation. It adds custom nodes for loading SDXL base models, InsightFace, ID ControlNet, and the InstantID IP-Adapter. Base models can be loaded locally or downloaded from Hugging Face. The generation node accepts a face reference and can optionally use a pose reference focused around the face. Users can tune IP-Adapter strength, ControlNet conditioning, steps, guidance, seed, and face enhancement. ... -
4
Video Diffusion - Pytorch
Implementation of Video Diffusion Models
...For conditioning on text, they derived text embeddings by first passing the tokenized text through BERT-large. You can also directly pass in the descriptions of the video as strings, if you plan on using BERT-base for text conditioning. This repository also contains a handy Trainer class for training on a folder of gifs. Each gif must be of the correct dimensions image_size and num_frames. -
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
5
ChatGPT Retrieval Plugin
The ChatGPT Retrieval Plugin lets you easily find personal documents
...It can serve as a custom GPT plugin or function-calling backend so that a chat session can “look up” relevant documents based on user queries, inject those results into context, and respond more knowledgeably about a private knowledge base. The repo provides code for ingestion pipelines (embedding documents), APIs for querying, local server components, and privacy / PII detection modules. It also contains plugin manifest files (OpenAPI spec, plugin JSON) so that the retrieval backend can be registered in a plugin ecosystem. Because retrieval is often needed to make LLMs “know what’s in your docs” without leaking everything, this plugin aims to be a secure, flexible building block for retrieval-augmented generation (RAG) systems. -
6
DeiT (Data-efficient Image Transformers)
Official DeiT repository
...Its key idea is a specialized distillation strategy—including a learnable “distillation token”—that lets a transformer learn effectively from a CNN or transformer teacher on modest-scale datasets. The project provides compact ViT variants (Tiny/Small/Base) that achieve excellent accuracy–throughput trade-offs, making transformers practical beyond massive pretraining regimes. Training involves carefully tuned augmentations, regularization, and optimization schedules to stabilize learning and improve sample efficiency. The repo offers pretrained checkpoints, reference scripts, and ablation studies that clarify which ingredients matter most for data-efficient ViT training. -
7
SalesGPT
Context-aware AI Sales Agent to automate sales outreach
...SalesGPT is context-aware, which means it can understand what stage of a sales conversation it is in and act accordingly. Moreover, SalesGPT has access to tools, such as your own pre-defined product knowledge base, significantly reducing hallucinations. -
8
Bufferstack.IO IIoT-Gateway
IIoT Gateway for interfacing industrial,home automation applications
This is Bufferstack. IO IIoT Gateway based on LTS stable software base which allows one to develop, deploy and host IOT, IIoT based applications using NodeJS, Python, influxdb, mosquitto mqtt broker. This is live+install CD, and for better experience in using it, please install it on your HDD/VM/Cloud -
9
DeepSeek MoE
Towards Ultimate Expert Specialization in Mixture-of-Experts Language
...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. The repo publishes both Base and Chat variants of the 16B MoE model (deepseek-moe-16b) and provides evaluation results across benchmarks. It also includes a quick start with inference instructions (using Hugging Face Transformers) and guidance on fine-tuning (DeepSpeed, hyperparameters, quantization). The licensing is MIT for code, with a “Model License” applied to the models. -
Cut Data Warehouse Costs by 54%BigQuery delivers 54% lower TCO with exabyte scale and flexible pricing. Free migration tools handle the SQL translation automatically.
-
10
wxWidgets
A cross-platform GUI library
wxWidgets is a C++ library that lets developers create applications for Windows, Mac OS X, Linux and other platforms with a single code base. It has popular language bindings for Python, Perl, Ruby and many other languages, and unlike other cross-platform toolkits, wxWidgets gives applications a truly native look and feel because it uses the platform's native API rather than emulating the GUI. It's also extensive, free, open-source and mature. -
11
SSD in PyTorch 1.0
High quality, fast, modular reference implementation of SSD in PyTorch
This repository implements SSD (Single Shot MultiBox Detector). The implementation is heavily influenced by the projects ssd.pytorch, pytorch-ssd and maskrcnn-benchmark. This repository aims to be the code base for research based on SSD. Multi-GPU training and inference: We use DistributedDataParallel, you can train or test with arbitrary GPU(s), the training schema will change accordingly. Add your own modules without pain. We abstract backbone, Detector, BoxHead, BoxPredictor, etc. You can replace every component with your own code without changing the code base. ... -
12
Chinese-LLaMA-Alpaca 2
Chinese LLaMA-2 & Alpaca-2 Large Model Phase II Project
This project is developed based on the commercially available large model Llama-2 released by Meta. It is the second phase of the Chinese LLaMA&Alpaca large model project. The Chinese LLaMA-2 base model and the Alpaca-2 instruction fine-tuning large model are open-sourced. These models expand and optimize the Chinese vocabulary on the basis of the original Llama-2, use large-scale Chinese data for incremental pre-training, and further improve the basic semantics and command understanding of Chinese. Performance improvements. ... -
13
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. ... -
14
Knobjex Info Manager
Tool for PIM, mind-mapping, quality-management, knowledge-base.
Also available for knowledge-enthusiasts: https://github.com/some-avail/freekwensie Knobjex 5.01 released partially; windows setup forthcoming; go to tab "Files" to download . Added shortcut keys (chapter 5.3) , dark themes better supported, removed bugs. No database-changes. Knobjex (short for Knowledge Objects) is an information-manager. It has many potential uses, such as calendar, task-list and sticky notes. Knobjex can also handle more advanced use-cases such as... -
15
MMAction2
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
OpenMMLab's next generation video understanding toolbox and benchmark. MMAction2 is an open-source toolbox for video understanding based on PyTorch. It is a part of the OpenMMLab project. Modular design: We decompose a video understanding framework into different components. One can easily construct a customized video understanding framework by combining different modules. Support four major video understanding tasks: MMAction2 implements various algorithms for multiple video understanding... -
16
DeepKE
An Open Toolkit for Knowledge Graph Extraction and Construction
Supporting cnSchema, standard supervised setting, low-resource setting, document-level setting and multi-modal setting for knowledge base population. DeepKE is a knowledge extraction toolkit supporting cnSchema, standard supervised, low-resource, and document-level scenarios for entity, relation, and attribution extraction. It allows developers and researchers to customize datasets and models to extract information from unstructured texts. DeepKE supports low-resource settings with only a few labeled (e.g., 16/32 shot) instances for widespread information extraction tasks. ... -
17
Sweep AI
Sweep: AI-powered Junior Developer for small features and bug fixes
Let Sweep handle your tech debt so you can focus on the exciting problems. Sweep is an AI junior developer that transforms bug reports & feature requests into code changes. Describe bugs, small features, and refactors like you would to a junior developer and Sweep. -
18
RPA for Python
Python package for doing RPA
...TagUI is a leading open-source RPA software with tens of thousands of users. It was created in 2016-2017 when I left DBS Bank as a test automation engineer, for a one-year sabbatical to Eastern Europe. Most of its code base was written in Novi Sad Serbia. In 2018, I joined AI Singapore to continue development of TagUI. -
19
lora-svc
Singing voice change based on whisper, lora for singing voice clone
...Uni-SVC main branch is for singing voice clone based on whisper with speaker encoder and speaker adapter. Uni-SVC main target is to develop lora for SVC. With lora, maybe clone a singer just need 10 stence after 10 minutes train. Each singer is a plug-in of the base model. -
20
MySQL 2 Excel Exporter 3-105 [I.S.A]
MySQL 2 Excel: Exporter 3-105 [Improved.Simplified.Alternative]
'MySQL2Excel_Exporter' is an desktop application developed using python 3.6.8 and other add-on libaries. The application exports MySql tables as a excel file. MySQL2Excel_Exporter has two parts: 1) Export - converts all records in mySQL table into excel file 2) Export Filter - converts selected recorerds in mySQL table into excel file Compatible only for windows OS. -
21
ConvNeXt V2
Code release for ConvNeXt V2 model
ConvNeXt V2 is an evolution of the ConvNeXt architecture that co-designs convolutional networks alongside self-supervised learning. The V2 version introduces a fully convolutional masked autoencoder (FCMAE) framework where parts of the image are masked and the network reconstructs the missing content, marrying convolutional inductive bias with powerful pretraining. A key innovation is a new Global Response Normalization (GRN) layer added to the ConvNeXt backbone, which enhances feature... -
22
Classic HWUT
Software Unit Tests (Language Independent Approach)
...The flexible approach enables the inclusion of many types of tests, such as memory leak checks (using valgrind), coding rule checks, complexity checks, etc. Tests are run by a simple call to hwut in a base directory of a project. In particular for C, HWUT supports make file generation using 'sos' and 'sols' modes. Remote control-able function stubs may be generated using the 'stub' mode. Test cases can be generated using the 'gen' mode, and state machine walkers by the 'sm_walker' mode. Over the last decade HWUT has matured towards a full fledged unit test tool for a wide variety of applications. -
23
albert_zh
Implementation of A Lite Bert For Self-Supervised Learning Language
...It implements ALBERT with TensorFlow and provides Chinese pretrained models designed to reduce parameter size while preserving strong language understanding performance. The project includes several model variants, such as tiny, small, base, large, and xlarge-style releases, giving users options for speed, size, and accuracy tradeoffs. It also provides guidance for fine-tuning downstream tasks such as sentence-pair semantic similarity and Chinese classification benchmarks. The repository includes support paths for TensorFlow, PyTorch conversion, Keras loading, TensorFlow 2.0 loading, and TensorFlow Lite deployment for mobile scenarios. ... -
24
FormaVid
Small Business Appliance
...It is an excellent starting point for any developer(s) wishing to support the CMS or any of the other components, including the appliance itself. All components are stable, open source and well supported. The appliance is built using scripts so no hidden "monkey business" and you can choose a "compatible base distro" based on your needs: familiarity; performance; security; usability; etc. Please see https://sourceforge.net/p/formavid/code/ci/master/tree/INSTALL.txt for details. The appliance is specially designed to run on the Google Cloud Platform "Free Tier" https://formavid.org/gce and has it's own custom install script https://sourceforge.net/projects/formavid/files/gcloud-gce-deployment/download with instructions https://sourceforge.net/projects/formavid/files/ provided. -
25
Amazon Braket Ocean Plugin
A Python plugin for using Ocean with Amazon Braket
...You can also install from source by cloning this repository and running a pip install command in the root directory of the repository. This package provides samplers which use Braket solvers. These samplers extend abstract base classes provided in Ocean's dimod and thus have the same interfaces as other samplers in Ocean.
