dolma

Dolma is a dataset and toolkit for curating large datasets for (pre)-training ML models. The dataset consists of 3 trillion tokens from a diverse mix of web content, academic publications, code, books, and encyclopedic materials. The toolkit provides high-performance, portable, and extensible tools for processing, tagging, and deduplicating documents. Key features of the toolkit include built-in taggers, fast deduplication, and cloud support.

Datasets is a repository that provides a collection of various datasets for machine learning and data analysis projects. It includes datasets in different formats such as CSV, JSON, and Excel, covering a wide range of topics including finance, healthcare, marketing, and more. The repository aims to help data scientists, researchers, and students access high-quality datasets for training models, conducting experiments, and exploring data analysis techniques.

Sycamore is a conversational search and analytics platform for complex unstructured data, such as documents, presentations, transcripts, embedded tables, and internal knowledge repositories. It retrieves and synthesizes high-quality answers through bringing AI to data preparation, indexing, and retrieval. Sycamore makes it easy to prepare unstructured data for search and analytics, providing a toolkit for data cleaning, information extraction, enrichment, summarization, and generation of vector embeddings that encapsulate the semantics of data. Sycamore uses your choice of generative AI models to make these operations simple and effective, and it enables quick experimentation and iteration. Additionally, Sycamore uses OpenSearch for indexing, enabling hybrid (vector + keyword) search, retrieval-augmented generation (RAG) pipelining, filtering, analytical functions, conversational memory, and other features to improve information retrieval.

Merlin is a groundbreaking model capable of generating natural language responses intricately linked with object trajectories of multiple images. It excels in predicting and reasoning about future events based on initial observations, showcasing unprecedented capability in future prediction and reasoning. Merlin achieves state-of-the-art performance on the Future Reasoning Benchmark and multiple existing multimodal language models benchmarks, demonstrating powerful multi-modal general ability and foresight minds.

vLLM is a fast and easy-to-use library for LLM inference and serving. It is designed to be efficient, flexible, and easy to use. vLLM can be used to serve a variety of LLM models, including Hugging Face models. It supports a variety of decoding algorithms, including parallel sampling, beam search, and more. vLLM also supports tensor parallelism for distributed inference and streaming outputs. It is open-source and available on GitHub.

Deep Lake is a Database for AI powered by a storage format optimized for deep-learning applications. Deep Lake can be used for: 1. Storing data and vectors while building LLM applications 2. Managing datasets while training deep learning models Deep Lake simplifies the deployment of enterprise-grade LLM-based products by offering storage for all data types (embeddings, audio, text, videos, images, pdfs, annotations, etc.), querying and vector search, data streaming while training models at scale, data versioning and lineage, and integrations with popular tools such as LangChain, LlamaIndex, Weights & Biases, and many more. Deep Lake works with data of any size, it is serverless, and it enables you to store all of your data in your own cloud and in one place. Deep Lake is used by Intel, Bayer Radiology, Matterport, ZERO Systems, Red Cross, Yale, & Oxford.

Docs2KG is a tool designed for constructing a unified knowledge graph from heterogeneous documents. It addresses the challenges of digitizing diverse unstructured documents and constructing a high-quality knowledge graph with less effort. The tool combines bottom-up and top-down approaches, utilizing a human-LLM collaborative interface to enhance the generated knowledge graph. It organizes the knowledge graph into MetaKG, LayoutKG, and SemanticKG, providing a comprehensive view of document content. Docs2KG aims to streamline the process of knowledge graph construction and offers metrics for evaluating the quality of automatic construction.

The LLM course is divided into three parts: 1. 🧩 **LLM Fundamentals** covers essential knowledge about mathematics, Python, and neural networks. 2. 🧑‍🔬 **The LLM Scientist** focuses on building the best possible LLMs using the latest techniques. 3. 👷 **The LLM Engineer** focuses on creating LLM-based applications and deploying them. For an interactive version of this course, I created two **LLM assistants** that will answer questions and test your knowledge in a personalized way: * 🤗 **HuggingChat Assistant**: Free version using Mixtral-8x7B. * 🤖 **ChatGPT Assistant**: Requires a premium account. ## 📝 Notebooks A list of notebooks and articles related to large language models. ### Tools | Notebook | Description | Notebook | |----------|-------------|----------| | 🧐 LLM AutoEval | Automatically evaluate your LLMs using RunPod |  | | 🥱 LazyMergekit | Easily merge models using MergeKit in one click. |  | | 🦎 LazyAxolotl | Fine-tune models in the cloud using Axolotl in one click. |  | | ⚡ AutoQuant | Quantize LLMs in GGUF, GPTQ, EXL2, AWQ, and HQQ formats in one click. |  | | 🌳 Model Family Tree | Visualize the family tree of merged models. |  | | 🚀 ZeroSpace | Automatically create a Gradio chat interface using a free ZeroGPU. |  |

ReaLHF is a distributed system designed for efficient RLHF training with Large Language Models (LLMs). It introduces a novel approach called parameter reallocation to dynamically redistribute LLM parameters across the cluster, optimizing allocations and parallelism for each computation workload. ReaL minimizes redundant communication while maximizing GPU utilization, achieving significantly higher Proximal Policy Optimization (PPO) training throughput compared to other systems. It supports large-scale training with various parallelism strategies and enables memory-efficient training with parameter and optimizer offloading. The system seamlessly integrates with HuggingFace checkpoints and inference frameworks, allowing for easy launching of local or distributed experiments. ReaLHF offers flexibility through versatile configuration customization and supports various RLHF algorithms, including DPO, PPO, RAFT, and more, while allowing the addition of custom algorithms for high efficiency.

EmbedJs is a NodeJS framework that simplifies RAG application development by efficiently processing unstructured data. It segments data, creates relevant embeddings, and stores them in a vector database for quick retrieval.

RAG Foundry is a library designed to enhance Large Language Models (LLMs) by fine-tuning models on RAG-augmented datasets. It helps create training data, train models using parameter-efficient finetuning (PEFT), and measure performance using RAG-specific metrics. The library is modular, customizable using configuration files, and facilitates prototyping with various RAG settings and configurations for tasks like data processing, retrieval, training, inference, and evaluation.

Macaw-LLM is a pioneering multi-modal language modeling tool that seamlessly integrates image, audio, video, and text data. It builds upon CLIP, Whisper, and LLaMA models to process and analyze multi-modal information effectively. The tool boasts features like simple and fast alignment, one-stage instruction fine-tuning, and a new multi-modal instruction dataset. It enables users to align multi-modal features efficiently, encode instructions, and generate responses across different data types.

RAG-FiT is a library designed to improve Language Models' ability to use external information by fine-tuning models on specially created RAG-augmented datasets. The library assists in creating training data, training models using parameter-efficient finetuning (PEFT), and evaluating performance using RAG-specific metrics. It is modular, customizable via configuration files, and facilitates fast prototyping and experimentation with various RAG settings and configurations.

pyLLMSearch is an advanced RAG system that offers a convenient question-answering system with a simple YAML-based configuration. It enables interaction with multiple collections of local documents, with improvements in document parsing, hybrid search, chat history, deep linking, re-ranking, customizable embeddings, and more. The package is designed to work with custom Large Language Models (LLMs) from OpenAI or installed locally. It supports various document formats, incremental embedding updates, dense and sparse embeddings, multiple embedding models, 'Retrieve and Re-rank' strategy, HyDE (Hypothetical Document Embeddings), multi-querying, chat history, and interaction with embedded documents using different models. It also offers simple CLI and web interfaces, deep linking, offline response saving, and an experimental API.

MathPile is a generative AI tool designed for math, offering a diverse and high-quality math-centric corpus comprising about 9.5 billion tokens. It draws from various sources such as textbooks, arXiv, Wikipedia, ProofWiki, StackExchange, and web pages, catering to different educational levels and math competitions. The corpus is meticulously processed to ensure data quality, with extensive documentation and data contamination detection. MathPile aims to enhance mathematical reasoning abilities of language models.

Dolma is a dataset and toolkit for curating large datasets for (pre)-training ML models. The dataset consists of 3 trillion tokens from a diverse mix of web content, academic publications, code, books, and encyclopedic materials. The toolkit provides high-performance, portable, and extensible tools for processing, tagging, and deduplicating documents. Key features of the toolkit include built-in taggers, fast deduplication, and cloud support.

LLM Datasets is a repository containing high-quality datasets, tools, and concepts for LLM fine-tuning. It provides datasets with characteristics like accuracy, diversity, and complexity to train large language models for various tasks. The repository includes datasets for general-purpose, math & logic, code, conversation & role-play, and agent & function calling domains. It also offers guidance on creating high-quality datasets through data deduplication, data quality assessment, data exploration, and data generation techniques.

NeMo Curator is a GPU-accelerated open-source framework designed for efficient large language model data curation. It provides scalable dataset preparation for tasks like foundation model pretraining, domain-adaptive pretraining, supervised fine-tuning, and parameter-efficient fine-tuning. The library leverages GPUs with Dask and RAPIDS to accelerate data curation, offering customizable and modular interfaces for pipeline expansion and model convergence. Key features include data download, text extraction, quality filtering, deduplication, downstream-task decontamination, distributed data classification, and PII redaction. NeMo Curator is suitable for curating high-quality datasets for large language model training.

AI-in-a-Box is a curated collection of solution accelerators that can help engineers establish their AI/ML environments and solutions rapidly and with minimal friction, while maintaining the highest standards of quality and efficiency. It provides essential guidance on the responsible use of AI and LLM technologies, specific security guidance for Generative AI (GenAI) applications, and best practices for scaling OpenAI applications within Azure. The available accelerators include: Azure ML Operationalization in-a-box, Edge AI in-a-box, Doc Intelligence in-a-box, Image and Video Analysis in-a-box, Cognitive Services Landing Zone in-a-box, Semantic Kernel Bot in-a-box, NLP to SQL in-a-box, Assistants API in-a-box, and Assistants API Bot in-a-box.

LangChain Rust is a library for building applications with Large Language Models (LLMs) through composability. It provides a set of tools and components that can be used to create conversational agents, document loaders, and other applications that leverage LLMs. LangChain Rust supports a variety of LLMs, including OpenAI, Azure OpenAI, Ollama, and Anthropic Claude. It also supports a variety of embeddings, vector stores, and document loaders. LangChain Rust is designed to be easy to use and extensible, making it a great choice for developers who want to build applications with LLMs.

Sparrow is an innovative open-source solution for efficient data extraction and processing from various documents and images. It seamlessly handles forms, invoices, receipts, and other unstructured data sources. Sparrow stands out with its modular architecture, offering independent services and pipelines all optimized for robust performance. One of the critical functionalities of Sparrow - pluggable architecture. You can easily integrate and run data extraction pipelines using tools and frameworks like LlamaIndex, Haystack, or Unstructured. Sparrow enables local LLM data extraction pipelines through Ollama or Apple MLX. With Sparrow solution you get API, which helps to process and transform your data into structured output, ready to be integrated with custom workflows. Sparrow Agents - with Sparrow you can build independent LLM agents, and use API to invoke them from your system. **List of available agents:** * **llamaindex** - RAG pipeline with LlamaIndex for PDF processing * **vllamaindex** - RAG pipeline with LLamaIndex multimodal for image processing * **vprocessor** - RAG pipeline with OCR and LlamaIndex for image processing * **haystack** - RAG pipeline with Haystack for PDF processing * **fcall** - Function call pipeline * **unstructured-light** - RAG pipeline with Unstructured and LangChain, supports PDF and image processing * **unstructured** - RAG pipeline with Weaviate vector DB query, Unstructured and LangChain, supports PDF and image processing * **instructor** - RAG pipeline with Unstructured and Instructor libraries, supports PDF and image processing. Works great for JSON response generation

Open-DocLLM is an open-source project that addresses data extraction and processing challenges using OCR and LLM technologies. It consists of two main layers: OCR for reading document content and LLM for extracting specific content in a structured manner. The project offers a larger context window size compared to JP Morgan's DocLLM and integrates tools like Tesseract OCR and Mistral for efficient data analysis. Users can run the models on-premises using LLM studio or Ollama, and the project includes a FastAPI app for testing purposes.

This repository provides code to deploy a chatbot powered by Multi-Model and Multi-RAG using AWS CDK on AWS. Users can experiment with various Large Language Models and Multimodal Language Models from different providers. The solution supports Amazon Bedrock, Amazon SageMaker self-hosted models, and third-party providers via API. It also offers additional resources like AWS Generative AI CDK Constructs and Project Lakechain for building generative AI solutions and document processing. The roadmap and authors are listed, along with contributors. The library is licensed under the MIT-0 License with information on changelog, code of conduct, and contributing guidelines. A legal disclaimer advises users to conduct their own assessment before using the content for production purposes.

This repository contains a minimal, clean code implementation of the Byte Pair Encoding (BPE) algorithm, commonly used in LLM tokenization. The BPE algorithm is "byte-level" because it runs on UTF-8 encoded strings. This algorithm was popularized for LLMs by the GPT-2 paper and the associated GPT-2 code release from OpenAI. Sennrich et al. 2015 is cited as the original reference for the use of BPE in NLP applications. Today, all modern LLMs (e.g. GPT, Llama, Mistral) use this algorithm to train their tokenizers. There are two Tokenizers in this repository, both of which can perform the 3 primary functions of a Tokenizer: 1) train the tokenizer vocabulary and merges on a given text, 2) encode from text to tokens, 3) decode from tokens to text. The files of the repo are as follows: 1. minbpe/base.py: Implements the `Tokenizer` class, which is the base class. It contains the `train`, `encode`, and `decode` stubs, save/load functionality, and there are also a few common utility functions. This class is not meant to be used directly, but rather to be inherited from. 2. minbpe/basic.py: Implements the `BasicTokenizer`, the simplest implementation of the BPE algorithm that runs directly on text. 3. minbpe/regex.py: Implements the `RegexTokenizer` that further splits the input text by a regex pattern, which is a preprocessing stage that splits up the input text by categories (think: letters, numbers, punctuation) before tokenization. This ensures that no merges will happen across category boundaries. This was introduced in the GPT-2 paper and continues to be in use as of GPT-4. This class also handles special tokens, if any. 4. minbpe/gpt4.py: Implements the `GPT4Tokenizer`. This class is a light wrapper around the `RegexTokenizer` (2, above) that exactly reproduces the tokenization of GPT-4 in the tiktoken library. The wrapping handles some details around recovering the exact merges in the tokenizer, and the handling of some unfortunate (and likely historical?) 1-byte token permutations. Finally, the script train.py trains the two major tokenizers on the input text tests/taylorswift.txt (this is the Wikipedia entry for her kek) and saves the vocab to disk for visualization. This script runs in about 25 seconds on my (M1) MacBook. All of the files above are very short and thoroughly commented, and also contain a usage example on the bottom of the file.

ScandEval is a framework for evaluating pretrained language models on mono- or multilingual language tasks. It provides a unified interface for benchmarking models on a variety of tasks, including sentiment analysis, question answering, and machine translation. ScandEval is designed to be easy to use and extensible, making it a valuable tool for researchers and practitioners alike.

Dolma is a dataset and toolkit for curating large datasets for (pre)-training ML models. The dataset consists of 3 trillion tokens from a diverse mix of web content, academic publications, code, books, and encyclopedic materials. The toolkit provides high-performance, portable, and extensible tools for processing, tagging, and deduplicating documents. Key features of the toolkit include built-in taggers, fast deduplication, and cloud support.

Unitxt is a customizable library for textual data preparation and evaluation tailored to generative language models. It natively integrates with common libraries like HuggingFace and LM-eval-harness and deconstructs processing flows into modular components, enabling easy customization and sharing between practitioners. These components encompass model-specific formats, task prompts, and many other comprehensive dataset processing definitions. The Unitxt-Catalog centralizes these components, fostering collaboration and exploration in modern textual data workflows. Beyond being a tool, Unitxt is a community-driven platform, empowering users to build, share, and advance their pipelines collaboratively.

SynCode is a novel framework for the grammar-guided generation of Large Language Models (LLMs) that ensures syntactically valid output with respect to defined Context-Free Grammar (CFG) rules. It supports general-purpose programming languages like Python, Go, SQL, JSON, and more, allowing users to define custom grammars using EBNF syntax. The tool compares favorably to other constrained decoders and offers features like fast grammar-guided generation, compatibility with HuggingFace Language Models, and the ability to work with various decoding strategies.

Awesome-LLM-Large-Language-Models-Notes is a repository that provides a comprehensive collection of information on various Large Language Models (LLMs) classified by year, size, and name. It includes details on known LLM models, their papers, implementations, and specific characteristics. The repository also covers LLM models classified by architecture, must-read papers, blog articles, tutorials, and implementations from scratch. It serves as a valuable resource for individuals interested in understanding and working with LLMs in the field of Natural Language Processing (NLP).

The multimodal cognitive AI repository focuses on research work related to multimodal cognitive artificial intelligence. It explores the integration of multiple modes of data such as text, images, and audio to enhance AI systems' cognitive capabilities. The repository likely contains code, datasets, and research papers related to multimodal AI applications, including natural language processing, computer vision, and audio processing. Researchers and developers interested in advancing AI systems' understanding of multimodal data can find valuable resources and insights in this repository.

Awesome-LLM-Constrained-Decoding is a curated list of papers, code, and resources related to constrained decoding of Large Language Models (LLMs). The repository aims to facilitate reliable, controllable, and efficient generation with LLMs by providing a comprehensive collection of materials in this domain.