44 dependents
| Package | Description | Downloads/month |
|---|---|---|
| Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-R1, ... | 171K | |
| An event-driven framework designed to build and orchestrate multi-agent AI syste... | 83K | |
| An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ ... | 75K | |
| OpenCompass is an LLM evaluation platform, supporting a wide range of models (LL... | 10K | |
| Open-Source Evaluation for GenAI Applications. | 6K | |
| document QA(RAG) package using langchain and chromadb | 6K | |
| 6K | ||
| OpenCompass is an LLM evaluation platform, supporting a wide range of models (Ll... | 5K | |
| Flexible RAG (Retrieval-Augmented Generation) framework for building AI applicat... | 4K | |
| A library for efficient Retrieval-Augmented Generation research | 3K | |
| Explore State-of-the-Art Materials Design Methods: https://www.nature.com/articl... | 2K | |
| Here we collected some online and offline models for text tagging. | 1K | |
| Huggingface bolts for geniusrise | 1K | |
| A Python package for RAG Evaluation | 824 | |
| Text components powering LLMs & SLMs for geniusrise framework | 551 | |
| Here I collected some online and offline models for text tagging. | 444 | |
| A Plug-and-Play and Comprehensive evaluation framework specifically for long-con... | 431 | |
| Moonshot - A simple and modular tool to evaluate and red-team any LLM applicatio... | 400 | |
| YiVal is an open-source project designed to revolutionize the way developers and... | 321 | |
| A Python package for memory-augmented retrieval-augmented generation | 306 | |
| tokenizers for pegasus | 296 | |
| Official implementation of GLUE3D: General Language Understanding Evaluation for... | 253 | |
| State-of-the-art Question Answering | 236 | |
| document QA(RAG) package(light weight version) using langchain and chromadb | 226 | |
| Toolkit for Active Learning in Generative Tasks | 203 | |
| Interactive and Iterative Prompt Mutation Interface for LLM Developers and Evalu... | 193 | |
| Export Camel toolkits as MCP servers | 193 | |
| Transformers Reinforcement and Imitation Learning Library | 165 | |
| DELTA is a deep learning based natural language and speech processing platform. ... | 153 | |
| Packages for zyz. | 152 | |
| Automatic text metrics (BLEU, ROUGE, METEOR, +++) | 121 | |
| This package is model compression toolkit for large language models and diffusio... | 119 | |
| structre context for code project | 110 | |
| structre context for code project | 105 | |
| Measure Gen AI quality and track experiments | 78 | |
| ScreenSuite | 76 | |
| Ext-Oracle Summarization: extractive summarization that maximize ROUGE w.r.t. ta... | 76 | |
| PAI EasyNLP Toolkit | 76 | |
| Calculate the BLEU, ROUGE, PPL scores of large models | 74 | |
| ScreenSuite | 60 | |
| An Open-Source Framework for Prompt-Learning. | 58 | |
| ScreenSuite | 35 | |
| SAGE Framework - 用户空间组件 (合并 sage-lib, sage-plugins 和 sage-examples) | 1 | |
| SAGE Framework - 核心API和前端统一框架，包含用户核心API接口 | 1 |
