Search Results for "inference"
Sort By:
Showing 7 open source projects for "inference"
View related business solutions-
Ango Hub | All-in-one data labeling platformAI-Assisted features of the Ango Hub will automate your AI data workflows to improve data labeling efficiency and model RLHF, all while allowing domain experts to focus on providing high-quality data.
-
AI-Powered Identity GovernanceDefine governance policies, manage access, and optimize licenses with unified visibility across every identity, app, and file.
-
1
UForm
Multi-Modal Neural Networks for Semantic Search, based on Mid-Fusion
UForm is a Multi-Modal Modal Inference package, designed to encode Multi-Lingual Texts, Images, and, soon, Audio, Video, and Documents, into a shared vector space! It comes with a set of homonymous pre-trained networks available on HuggingFace portal and extends the transfromers package to support Mid-fusion Models. Late-fusion models encode each modality independently, but into one shared vector space. -
2
ModernBERT
Bringing BERT into modernity via both architecture changes and scaling
...The goal of the project is to bring BERT-style models up to date with the capabilities of modern large language models while preserving the strengths of bidirectional encoder architectures used for tasks such as classification, retrieval, and semantic search. ModernBERT introduces architectural improvements that enhance both training efficiency and inference performance, making the model more suitable for modern large-scale machine learning pipelines. The repository also includes FlexBERT, a modular framework that allows developers to experiment with different encoder building blocks and configurations when constructing new models. -
3
Pixeltable
Data Infrastructure providing an approach to multimodal AI workloads
Pixeltable is an open-source Python data infrastructure framework designed to support the development of multimodal AI applications. The system provides a declarative interface for managing the entire lifecycle of AI data pipelines, including storage, transformation, indexing, retrieval, and orchestration of datasets. Unlike traditional architectures that require multiple tools such as databases, vector stores, and workflow orchestrators, Pixeltable unifies these functions within a... -
4
FlagEmbedding
Retrieval and Retrieval-augmented LLMs
...FlagEmbedding includes a family of models known as BGE (BAAI General Embedding), which are designed to achieve strong performance across multilingual and cross-lingual retrieval benchmarks. The toolkit provides infrastructure for inference, fine-tuning, evaluation, and dataset preparation, enabling developers to train custom embedding models for specific domains or applications. It also includes reranker models that refine search results by re-evaluating candidate documents using cross-encoder architectures, improving retrieval accuracy in complex queries. -
Empower Your Contact Center with Human-Like AI ConversationsEnterprise Bot, based in Switzerland, is a pioneer in Conversational AI, Process Automation, and Generative AI. With the trust of esteemed enterprise giants across industries like Generali, SIX, SBB, DHL, and SWICA, Enterprise Bot is revolutionizing both customer and employee experiences. Through its advanced integration with Large Language Models (LLM) such as ChatGPT and Llama 2, and its unique patent-pending DocBrain technology, the company delivers unparalleled personalization, active engagement, and omnichannel solutions across platforms like email, voice, and chat. Furthermore, Enterprise Bot integrates with existing core systems, such as SAP, CRMs, Confluence and more, and with its proprietary middleware, Blitzico, enables the AI to not only respond to queries but also take action to resolve them. This dedication to innovation in four main use case areas, Customer Support, Sales and Marketing, Knowledge Management and Digital Coworker, elevates both CX and employee productivity.
-
5
ViMax
Director, Screenwriter, Producer, and Video Generator All-in-One
...It integrates components like visual encoders, cross-modal fusion techniques, and reasoning modules so that users can go beyond simple captioning or classification to perform tasks such as visual question answering, multi-image inference, and structured scene understanding. ViMax’s design accommodates large image sets and supports retrieval augmentation, enabling it to work with external image databases, supplementary metadata, and semantic search to enhance context awareness. The system aims to bridge foundational vision backbones and generative language models through adapters and fusion layers that maximize both signal integration and reasoning depth, and includes utility pipelines for training, evaluation, and deployment. -
6
Language Models
Explore large language models in 512MB of RAM
...The project focuses on enabling developers and students to explore language model capabilities without needing expensive GPUs or large cloud infrastructures. 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. ... -
7
Hugging Face Transformer
CPU/GPU inference server for Hugging Face transformer models
...At Lefebvre Dalloz we run in-production semantic search engines in the legal domain, in the non-marketing language it's a re-ranker, and we based ours on Transformer. In that setup, latency is key to providing a good user experience, and relevancy inference is done online for hundreds of snippets per user query. Most tutorials on Transformer deployment in production are built over Pytorch and FastAPI. Both are great tools but not very performant in inference. Then, if you spend some time, you can build something over ONNX Runtime and Triton inference server. You will usually get from 2X to 4X faster inference compared to vanilla Pytorch. ...
- Previous
- You're on page 1
- Next
