Autonomous AI agents that perform tasks independently
A collection of open source, actively maintained web apps for LLM applications.
日本語LLMまとめ - Overview of Japanese LLMs.
The paper list of the review on LLMs in medicine.
A curated list of Awesome LLM Inference Paper with codes.
A curated list of Multi-modal Large Language Model in 3D world, including 3D understanding, reasoning, generation, and embodied agents.
...morea curated collection of datasets specifically designed for chatbot training, including links, size, language, usage, and a brief description of each dataset
...more整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
Applying Large language models (LLMs) for diverse optimization tasks (Opt) is an emerging research area. This is a collection of references and papers of LLM4Opt.
...moreThis paper list focuses on the theoretical or empirical analysis of language models, e.g., the learning dynamics, expressive capacity, interpretability, generalization, and other interesting topics.
...morean evaluation benchmark focused on ancient Chinese language comprehension.
LLM application: DeepSeek-Coder-v2-16|236B-MOE
LLM application: RecurrentGemma-2B
LLM application: Pythia-1|1.4|2.8|6.9|12B
Open-Source Toolkit for Efficient Unstructured Data Processing with Pre-built Modules and Local to Cluster Scalability.
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
...moreA powerful tool for creating high-quality training datasets for Large Language Models
a lightweight LLM evaluation suite that Hugging Face has been using internally.
Eval tools by OpenAI.
a repository for evaluating open language models.
This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.
...morea lean, efficient, and easy-to-hack codebase to research LLMs.
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
Minimalistic large language model 3D-parallelism training.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
...more