GitHub - CambioML/uniflow-llm-based-pdf-extraction-text-cleaning-data-clustering: LLM-based text extraction from unstructured data like PDFs, Words and HTMLs. Transform and cluster the text into your desired format. Less information loss, more interpretation, and faster...
Sugarcane AI is an open-source framework designed to simplify and accelerate LLM app development. With a focus on fine-tuned Language Models (LLMs), prompt management, and Workflow Plugins, Sugarcane AI empowers developers to build, train, and manage complex LLM applications effortlessly. 🎉
Why Sugarcane AI? : Key Features of Microservices Framewor... See more
Why Sugarcane AI? : Key Features of Microservices Framewor... See more
sugarcane-ai • GitHub - sugarcane-ai/sugarcane-ai.github.io
Indexify - Extraction and Retrieval from Videos, PDF and Audio for Interactive AI Applications
Indexify is an open-source engine for buidling fast data pipelines for unstructured data(video, audio, images and documents) using re-usable extractors for embedding, transformatio... See more
LLM applications backed by Indexify will never answer outdated information.
Indexify is an open-source engine for buidling fast data pipelines for unstructured data(video, audio, images and documents) using re-usable extractors for embedding, transformatio... See more
tensorlakeai • GitHub - tensorlakeai/indexify: A scalable realtime and continuous indexing engine for Unstructured Data to build Generative AI Applications
TL;DR
LLMLingua utilizes a compact, well-trained language model (e.g., GPT2-small, LLaMA-7B) to identify and remove non-essential tokens in prompts. This approach enables efficient inference with large language models (LLMs), achieving up to 20x compression with minimal performance loss.
... See more
LLMLingua utilizes a compact, well-trained language model (e.g., GPT2-small, LLaMA-7B) to identify and remove non-essential tokens in prompts. This approach enables efficient inference with large language models (LLMs), achieving up to 20x compression with minimal performance loss.
... See more
microsoft • GitHub - microsoft/LLMLingua: To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
DataTrove
DataTrove is a library to process, filter and deduplicate text data at a very large scale. It provides a set of prebuilt commonly used processing blocks with a framework to easily add custom functionality.
DataTrove processing pipelines are platform-agnostic, running out of the box locally or on a slurm cluster. Its (relatively) low memory... See more
DataTrove is a library to process, filter and deduplicate text data at a very large scale. It provides a set of prebuilt commonly used processing blocks with a framework to easily add custom functionality.
DataTrove processing pipelines are platform-agnostic, running out of the box locally or on a slurm cluster. Its (relatively) low memory... See more