Statistics for topic nlp

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

The Fastest State-of-the-Art Static Embeddings in the World

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. W...

The Fastest State-of-the-Art Static Embeddings in the World

Source for Who're Interested in Data!

4th Place Solution for the Kaggle Competition: LMSYS - Chatbot Arena Human Preference Predictions

InvestorGPT is an AI agent that analyzes the stock that dropped in its price recently and calculates chance for the company to recover the stock price back.

PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

The Fastest State-of-the-Art Static Embeddings in the World

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

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。

This project aims to emulate some of the advanced reasoning capabilities seen in models like OpenAI's o1. It does not claim to replicate the exact functionality or performance of o1.

The Fastest State-of-the-Art Static Embeddings in the World

Source for Who're Interested in Data!

4th Place Solution for the Kaggle Competition: LMSYS - Chatbot Arena Human Preference Predictions

PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides

PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides

Use multiple LLM backends in a single crate, simple builder-based configuration, and built-in prompt chaining & templating.

Inference engine for GLiNER models, in Rust

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Large Concept Models: Language modeling in a sentence representation space

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。

PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides

FlexRAG: A RAG Framework for Information Retrieval and Generation.

为了翻译拼音缩写，基于Bert训练的模型，在命名实体识别，情感分析等多种任务上有应用潜力。中文拼写纠错 Chinese Spelling Correction (CSC)，互联网黑话，拼音缩写

This project aims to emulate some of the advanced reasoning capabilities seen in models like OpenAI's o1. It does not claim to replicate the exact functionality or performance of o1.

Use multiple LLM backends in a single crate, simple builder-based configuration, and built-in prompt chaining & templating.

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

《大语言模型》作者：赵鑫，李军毅，周昆，唐天一，文继荣

AdalFlow: The library to build & auto-optimize LLM applications.

🦛 CHONK your texts with Chonkie ✨ - The no-nonsense RAG chunking library

Large Concept Models: Language modeling in a sentence representation space

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

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。

12 Weeks, 24 Lessons, AI for All!

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

Large Concept Models: Language modeling in a sentence representation space

中文羊驼大模型三期项目 (Chinese Llama-3 LLMs) developed from Meta Llama 3

Superlinked is a Python framework for AI Engineers building high-performance search & recommendation applications that combine structured and unstructured data.

Official repository for ICLR 2025 paper "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing". Your efficient and high-quality synthetic data generation pipeline!