# paddlepaddle/ernie

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/paddlepaddle-ernie).**

7,717 stars · 1,441 forks · Python · Apache-2.0

## Links

- GitHub: https://github.com/PaddlePaddle/ERNIE
- Homepage: https://ernie.baidu.com
- awesome-repositories: https://awesome-repositories.com/repository/paddlepaddle-ernie.md

## Topics

`ernie` `ernie-45` `ernie-45-vl` `erniekit` `llm` `vlm`

## Description

ERNIE is a development toolkit for training, fine-tuning, and deploying large language models built on the PaddlePaddle deep learning platform. It provides a comprehensive suite of core components, including an inference server for vision and language models, a training and fine-tuning toolkit, and a framework for building retrieval-augmented generation systems using private knowledge bases.

The project features multimodal AI models capable of reasoning across text, images, and video to perform complex visual understanding and information extraction. It distinguishes itself through specialized training methodologies for function calling and the use of mixture-of-experts architectures to enhance cross-modal reasoning.

The system covers a broad range of capabilities including industrial natural language processing deployment, visual mathematical reasoning, and document information extraction. Performance is addressed through quantization, hybrid-parallelism training, and disaggregated inference serving to optimize memory usage and throughput.

A web-based user interface is provided for supervising training processes and conducting interactive conversations.

## Tags

### Artificial Intelligence & ML

- [Model Inference Servers](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-inference-serving/engines-runtimes-servers/model-inference-servers.md) — Ships a production-ready server application that hosts vision and language models with quantization and hardware acceleration.
- [Large Language Model Training Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-training-and-tuning/training-frameworks/large-language-model-training-frameworks.md) — Provides a development toolkit for training, fine-tuning, and deploying large language models built on PaddlePaddle. ([source](https://github.com/paddlepaddle/ernie#readme))
- [Distributed Training](https://awesome-repositories.com/f/artificial-intelligence-ml/distributed-training-frameworks/distributed-training.md) — Provides tools for configuring data and model parallelism to train large neural networks across multiple devices.
- [Inference Acceleration](https://awesome-repositories.com/f/artificial-intelligence-ml/inference-acceleration.md) — Reduces memory footprints and latency by applying quantization, multi-expert collaboration, and disaggregation techniques. ([source](https://github.com/paddlepaddle/ernie#readme))
- [Knowledge Retrieval Systems](https://awesome-repositories.com/f/artificial-intelligence-ml/knowledge-retrieval-systems.md) — Provides a framework for building question-answering systems that surface information from private, domain-specific datasets.
- [LLM Development Toolkits](https://awesome-repositories.com/f/artificial-intelligence-ml/llm-development-toolkits.md) — Provides a development toolkit for training, fine-tuning, and deploying large language models built on the PaddlePaddle platform.
- [LLM Fine-Tuning Toolsets](https://awesome-repositories.com/f/artificial-intelligence-ml/llm-fine-tuning-toolsets.md) — Provides a comprehensive toolkit for supervised fine-tuning and parameter-efficient updates like LoRA for language models.
- [Multimodal Perception Models](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/architectures/multimodal-perception-models.md) — Ships models designed to interpret and analyze visual data, charts, and cross-modal inputs alongside text.
- [Multimodal Processing](https://awesome-repositories.com/f/artificial-intelligence-ml/multimodal-processing.md) — Reasons across text, images, and video using heterogeneous structures to perform complex visual understanding tasks. ([source](https://github.com/paddlepaddle/ernie#readme))
- [Multimodal Training](https://awesome-repositories.com/f/artificial-intelligence-ml/multimodal-training.md) — Processes textual and visual data simultaneously using mixture-of-experts to improve cross-modal reasoning and generation. ([source](https://github.com/paddlepaddle/ernie#readme))
- [Industrial NLP Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/natural-language-processing/nlp-applications/industrial-nlp-pipelines.md) — Provides a specialized set of tools to build and deploy industrial-grade natural language processing applications. ([source](https://github.com/paddlepaddle/ernie#readme))
- [Parameter Efficient Fine-Tuning](https://awesome-repositories.com/f/artificial-intelligence-ml/parameter-efficient-fine-tuning.md) — Provides memory-efficient adaptation techniques like LoRA to update a small subset of model parameters.
- [Visual Content Analysis](https://awesome-repositories.com/f/artificial-intelligence-ml/visual-content-analysis.md) — Extracts visual knowledge from images, documents, and charts to maintain high perception accuracy across datasets. ([source](https://github.com/paddlepaddle/ernie#readme))
- [Chat Bot Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/chat-bot-frameworks.md) — Provides tools for creating automated agents that interact with users through chat, web search, and function calling.
- [Visual Mathematical Reasoning](https://awesome-repositories.com/f/artificial-intelligence-ml/complex-problem-solving/visual-mathematical-reasoning.md) — Solves complex multimodal reasoning puzzles and mathematical visual tasks by combining visual perception with a thinking mode. ([source](https://github.com/paddlepaddle/ernie#readme))
- [Conversational Bot Development](https://awesome-repositories.com/f/artificial-intelligence-ml/conversational-bot-development.md) — Enables the creation of interactive chat interfaces and bots that integrate real-time web search for dynamic information delivery. ([source](https://github.com/paddlepaddle/ernie#readme))
- [RAG Document Retrieval](https://awesome-repositories.com/f/artificial-intelligence-ml/documentation-retrieval-engines/rag-document-retrieval.md) — Retrieves relevant snippets from local and private documents to provide grounded context for model responses.
- [Function Calling Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/function-calling-interfaces.md) — Trains models to recognize and execute external tool calls through specialized function call training methodologies. ([source](https://github.com/paddlepaddle/ernie#readme))
- [Information Extraction](https://awesome-repositories.com/f/artificial-intelligence-ml/information-extraction.md) — Extracts key data and performs deep information extraction from contracts using text recognition and language modeling. ([source](https://github.com/paddlepaddle/ernie#readme))
- [Instruction-Following Models](https://awesome-repositories.com/f/artificial-intelligence-ml/instruction-following-models.md) — Processes detailed user prompts and world knowledge to generate precise responses based on specific constraints. ([source](https://github.com/paddlepaddle/ernie#readme))
- [Mixture of Experts](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-training-and-tuning/fine-tuning-and-customization/model-customization/mixture-of-experts.md) — Supports routing and recording expert paths using a mixture-of-experts architecture to improve reasoning efficiency.
- [Preference Alignment](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-training-and-tuning/fine-tuning-and-customization/model-fine-tuning/fine-tuning-benchmarking/preference-alignment.md) — Optimizes task accuracy and aligns model outputs with human preferences using supervised fine-tuning methods. ([source](https://github.com/paddlepaddle/ernie#readme))
- [Multimodal Fine-Tuning](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-training-and-tuning/fine-tuning-and-customization/model-fine-tuning/multimodal-fine-tuning.md) — Enables customizing pre-trained models for general language or visual tasks using supervised fine-tuning and preference optimization. ([source](https://github.com/paddlepaddle/ernie#readme))
- [Model Deployment](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-training-and-tuning/fine-tuning-and-customization/model-fine-tuning/pre-trained-model-zoos/model-deployment.md) — Transforms trained language models into production-ready services for real-world industrial environments. ([source](https://github.com/paddlepaddle/ernie#readme))
- [Model Management Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/model-management-interfaces.md) — Ships a graphical user interface for supervising model training processes and conducting interactive conversations. ([source](https://github.com/paddlepaddle/ernie#readme))
- [Disaggregated Inference](https://awesome-repositories.com/f/artificial-intelligence-ml/model-optimization/inference-deployment/model-deployment-toolkits/distributed-deployment-utilities/disaggregated-inference.md) — Implements architectures that separate prefill and decode stages across distinct hardware nodes to reduce latency.
- [Model Performance Optimization](https://awesome-repositories.com/f/artificial-intelligence-ml/model-optimization/profiling-and-benchmarking/model-performance-optimization.md) — Enhances model speed and accuracy through quantization and hardware acceleration within the PaddlePaddle framework.
- [Quantization-Aware Training](https://awesome-repositories.com/f/artificial-intelligence-ml/model-quantization/quantization-aware-training.md) — Integrates low-precision arithmetic into the training loop to reduce model size while maintaining high accuracy.
- [Reasoning Models](https://awesome-repositories.com/f/artificial-intelligence-ml/reasoning-models.md) — Executes mathematical and knowledge-intensive tasks using specialized model architectures to achieve high-accuracy results. ([source](https://github.com/paddlepaddle/ernie#readme))
- [Training Memory Management](https://awesome-repositories.com/f/artificial-intelligence-ml/training-memory-management.md) — Eliminates padding and reduces GPU memory consumption by packing multiple data samples into a single sequence. ([source](https://github.com/paddlepaddle/ernie#readme))
- [Training Throughput Optimization](https://awesome-repositories.com/f/artificial-intelligence-ml/training-throughput-optimization.md) — Increases pre-training speed by using hybrid parallelism, mixed-precision formats, and hierarchical load balancing. ([source](https://github.com/paddlepaddle/ernie#readme))

### Part of an Awesome List

- [Large Language Model Deployments](https://awesome-repositories.com/f/awesome-lists/ai/local-model-deployment/large-language-model-deployments.md) — Executes resource-efficient training and inference workflows for large-scale models on private industrial hardware. ([source](https://github.com/paddlepaddle/ernie#readme))
- [Multimodal AI](https://awesome-repositories.com/f/awesome-lists/ai/multimodal-ai.md) — Builds models that bridge text, images, and video to perform complex visual understanding and reasoning.
- [Multimodal Models](https://awesome-repositories.com/f/awesome-lists/ai/multimodal-models.md) — Implements a model architecture capable of reasoning across text, images, and video for visual information extraction.
- [Natural Language Processing](https://awesome-repositories.com/f/awesome-lists/ai/natural-language-processing.md) — Listed in the “Natural Language Processing” section of the FunNLP awesome list.

### DevOps & Infrastructure

- [Inference Deployment](https://awesome-repositories.com/f/devops-infrastructure/inference-deployment.md) — Provides infrastructure and tools for hosting and serving language and vision models on multi-hardware setups. ([source](https://github.com/paddlepaddle/ernie#readme))