Tag

This paper introduces ReAct, an approach that integrates reasoning and acting in large language models (LLMs). ReAct enables LLMs to generate both reasoning traces and task-specific actions in an interleaved manner. This synergy allows reasoning to help induce, track, and update action plans, while actions interface with external sources like knowledge bases to gather more information, overcoming issues of hallucination and error propagation in prior methods.

LightRAG is an open-source framework designed for simple and fast Retrieval-Augmented Generation (RAG), integrating knowledge graphs, vector search, and efficient LLM-based processing to enhance question-answering over large document collections.

Processes and indexes digital evidence for forensic analysis (disk images, files, timelines). Offers high-speed carving, OCR (Tesseract), NER, similar-document/image and face search, audio transcription and scriptable parsers — Java-based and extensible for investigators.

Provides research-grade implementations and pretrained models for sequence tasks (translation, LM, speech). Offers multi-GPU training, fast generation (beam/sampling/lexical constraints), mixed-precision, and state sharding — aimed at researchers reproducing or extending papers.

Provides 150+ executed Jupyter notebooks and code that reproduce the book 'Machine Learning for Algorithmic Trading (2nd ed.)' — covers feature engineering, alternative-data signal extraction, backtesting, NLP, deep learning and reinforcement learning for trading; best for quant researchers and practitioners.

Provides unified model definitions and a single API for pretrained text, vision, audio, and multimodal models for both training and inference. Emphasizes cross-framework compatibility (PyTorch/TF/JAX), pipeline-based inference, and direct access to 1M+ Hub checkpoints.

Provides official documentation for the Transformers library — APIs, model definitions, training (Trainer), inference pipelines, tokenizers, and integrations for text, vision, audio and multimodal models. Focused on developer workflows and production use.

A 57-subject multiple-choice benchmark for measuring broad language understanding in LLMs; provides per-subject configs and test/dev/auxiliary_train splits for few-/zero-shot evaluation, widely used for model comparison and academic reporting.

Provides cleaned, per-language snapshots of Wikipedia articles (id, url, title, text) packaged as Hugging Face dataset configs (Parquet). Covers 300+ language configs and dated dumps — useful for language modeling, multilingual NLP, retrieval, and RAG pipelines.

Benchmark dataset of ~8.5k grade-school math word problems with step-by-step solutions and calculator annotations for evaluating multi-step arithmetic reasoning in language models. Provided in two configs (main and socratic) and commonly used for chain-of-thought prompting, fine-tuning, and verifier training.

Enables high-performance deployment and serving of popular open-source LLMs (Llama, Falcon, StarCoder, etc.) with production features like streaming, tensor parallelism, quantization and Prometheus metrics. Now in maintenance mode; recommended for teams needing an integrated HF inference stack.

Provides human preference comparison pairs and red-team conversation transcripts collected by Anthropic for training preference/reward models and studying harmful model behaviors; intended for RLHF and safety research, not for supervised fine-tuning of dialogue agents.