# Qwen

## Docs

- [Building Agents with Qwen](https://mintlify.wiki/QwenLM/Qwen/advanced/agent.md): Create intelligent agents that can reason, plan, and use tools effectively
- [Function Calling](https://mintlify.wiki/QwenLM/Qwen/advanced/function-calling.md): Learn how to use Qwen models to call functions and interact with external tools
- [Long Context Handling](https://mintlify.wiki/QwenLM/Qwen/advanced/long-context.md): Leverage Qwen models for processing long sequences up to 32K tokens
- [Using System Prompts Effectively](https://mintlify.wiki/QwenLM/Qwen/advanced/system-prompts.md): Customize Qwen model behavior with system prompts for role-playing, task setting, and behavior control
- [Tool Use and Integration](https://mintlify.wiki/QwenLM/Qwen/advanced/tool-use.md): Master ReAct prompting and tool integration patterns with Qwen models
- [Chat API](https://mintlify.wiki/QwenLM/Qwen/api/chat.md): Interact with Qwen models using the chat interface for conversational AI
- [GenerationConfig](https://mintlify.wiki/QwenLM/Qwen/api/generation-config.md): Configure text generation parameters for Qwen models
- [Model Loading API](https://mintlify.wiki/QwenLM/Qwen/api/model-loading.md): Load and initialize Qwen models for inference and fine-tuning
- [Chat Completions](https://mintlify.wiki/QwenLM/Qwen/api/openai/chat-completions.md): OpenAI-compatible chat completions endpoint for Qwen models
- [Models Endpoint](https://mintlify.wiki/QwenLM/Qwen/api/openai/models.md): List available models in OpenAI-compatible API
- [Streaming Responses](https://mintlify.wiki/QwenLM/Qwen/api/openai/streaming.md): Receive real-time token-by-token responses using Server-Sent Events
- [Tokenizer API](https://mintlify.wiki/QwenLM/Qwen/api/tokenizer.md): Encode and decode text for Qwen models
- [Training Arguments](https://mintlify.wiki/QwenLM/Qwen/api/training/arguments.md): Configure fine-tuning parameters for Qwen models
- [Data Format](https://mintlify.wiki/QwenLM/Qwen/api/training/data-format.md): Training data format specification for Qwen fine-tuning
- [LoRA Configuration](https://mintlify.wiki/QwenLM/Qwen/api/training/lora-config.md): Configure Low-Rank Adaptation for parameter-efficient fine-tuning
- [CLI Demo](https://mintlify.wiki/QwenLM/Qwen/demos/cli.md): Interactive command-line chat interface for Qwen models
- [Advanced Gradio Integration](https://mintlify.wiki/QwenLM/Qwen/demos/gradio.md): Enhanced Gradio features and custom implementations for Qwen models
- [Web Demo](https://mintlify.wiki/QwenLM/Qwen/demos/web.md): Gradio-based web interface for Qwen-Chat models
- [Docker Deployment](https://mintlify.wiki/QwenLM/Qwen/deployment/docker.md): Deploy Qwen models using Docker containers for simplified setup and consistent environments
- [FastChat Deployment](https://mintlify.wiki/QwenLM/Qwen/deployment/fastchat.md): Deploy Qwen with FastChat for a complete solution with web UI, OpenAI API, and advanced features
- [OpenAI-Compatible API Server](https://mintlify.wiki/QwenLM/Qwen/deployment/openai-api.md): Deploy Qwen with an OpenAI-compatible REST API for seamless integration
- [Deployment Overview](https://mintlify.wiki/QwenLM/Qwen/deployment/overview.md): Comprehensive guide to deploying Qwen models in production environments
- [Production Best Practices](https://mintlify.wiki/QwenLM/Qwen/deployment/production.md): Essential guidelines for deploying Qwen models in production environments
- [vLLM Deployment](https://mintlify.wiki/QwenLM/Qwen/deployment/vllm.md): Deploy Qwen with vLLM for high-performance, production-grade inference
- [Data Preparation](https://mintlify.wiki/QwenLM/Qwen/finetuning/data-preparation.md): Learn how to prepare and format training data for fine-tuning Qwen models
- [Full-Parameter Fine-tuning](https://mintlify.wiki/QwenLM/Qwen/finetuning/full-parameter.md): Train Qwen models by updating all parameters for maximum performance
- [LoRA Fine-tuning](https://mintlify.wiki/QwenLM/Qwen/finetuning/lora.md): Efficient parameter-efficient fine-tuning using Low-Rank Adaptation
- [Multi-node Distributed Training](https://mintlify.wiki/QwenLM/Qwen/finetuning/multinode.md): Scale Qwen fine-tuning across multiple machines for large models and datasets
- [Fine-tuning Overview](https://mintlify.wiki/QwenLM/Qwen/finetuning/overview.md): Learn about the different fine-tuning methods available for Qwen models
- [Q-LoRA Fine-tuning](https://mintlify.wiki/QwenLM/Qwen/finetuning/qlora.md): Memory-efficient fine-tuning using Quantized Low-Rank Adaptation
- [Basic Inference](https://mintlify.wiki/QwenLM/Qwen/inference/basic-usage.md): Get started with Qwen inference using simple examples
- [Batch Inference](https://mintlify.wiki/QwenLM/Qwen/inference/batch-inference.md): Efficiently process multiple inputs with batch inference
- [Using Qwen with ModelScope](https://mintlify.wiki/QwenLM/Qwen/inference/modelscope.md): Run Qwen models using the ModelScope platform
- [Multi-GPU Inference](https://mintlify.wiki/QwenLM/Qwen/inference/multi-gpu.md): Scale Qwen inference across multiple GPUs for large models
- [Streaming Responses](https://mintlify.wiki/QwenLM/Qwen/inference/streaming.md): Stream tokens in real-time for interactive applications
- [Using Qwen with Transformers](https://mintlify.wiki/QwenLM/Qwen/inference/transformers.md): Complete guide to running Qwen models with the Transformers library
- [Installation](https://mintlify.wiki/QwenLM/Qwen/installation.md): Complete installation guide for Qwen models and dependencies
- [Introduction](https://mintlify.wiki/QwenLM/Qwen/introduction.md): Qwen is a series of large language models from Alibaba Cloud, featuring models from 1.8B to 72B parameters with state-of-the-art performance
- [Base Models](https://mintlify.wiki/QwenLM/Qwen/models/base-models.md): Documentation for Qwen base pretrained models
- [Chat Models](https://mintlify.wiki/QwenLM/Qwen/models/chat-models.md): Documentation for Qwen chat-aligned models
- [Model Selection Guide](https://mintlify.wiki/QwenLM/Qwen/models/model-selection.md): Choose the right Qwen model for your use case
- [Model Overview](https://mintlify.wiki/QwenLM/Qwen/models/overview.md): Complete overview of the Qwen model family
- [GPTQ Quantization](https://mintlify.wiki/QwenLM/Qwen/quantization/gptq.md): Use AutoGPTQ to quantize Qwen models to Int4 and Int8
- [KV Cache Quantization](https://mintlify.wiki/QwenLM/Qwen/quantization/kv-cache.md): Compress attention cache to enable larger batch sizes and longer sequences
- [Quantization Overview](https://mintlify.wiki/QwenLM/Qwen/quantization/overview.md): Reduce memory usage and improve inference speed with model quantization
- [Performance Benchmarks](https://mintlify.wiki/QwenLM/Qwen/quantization/performance.md): Detailed performance analysis and optimization guidelines for quantized Qwen models
- [Quickstart](https://mintlify.wiki/QwenLM/Qwen/quickstart.md): Get started with Qwen in under 5 minutes
- [Benchmark Results](https://mintlify.wiki/QwenLM/Qwen/resources/benchmarks.md): Comprehensive benchmark results and performance comparisons for Qwen models
- [Changelog](https://mintlify.wiki/QwenLM/Qwen/resources/changelog.md): Version history and updates for Qwen models
- [FAQ](https://mintlify.wiki/QwenLM/Qwen/resources/faq.md): Frequently asked questions about Qwen models
- [Hardware Requirements](https://mintlify.wiki/QwenLM/Qwen/resources/hardware-requirements.md): Hardware specifications and memory requirements for running Qwen models
- [Technical Report](https://mintlify.wiki/QwenLM/Qwen/resources/technical-report.md): Technical overview and methodology for Qwen large language models
- [Tokenization](https://mintlify.wiki/QwenLM/Qwen/resources/tokenization.md): Detailed guide to Qwen's tokenization system and vocabulary
- [Troubleshooting](https://mintlify.wiki/QwenLM/Qwen/resources/troubleshooting.md): Common issues and solutions for Qwen models