# Structured JSON output

A multimodal large model launched by Tongyi Qianwen, supporting image and text generation and 128k long context processing, with multilingual capabilities.

The quantized model of Qwen2.5 VL 7B Instruct is a powerful multimodal model that supports image and text input and generates text output, with wide application value in multiple fields.

A vision-language model specifically designed to extract structured financial information from cheque images and generate JSON-formatted output containing key information such as cheque number, payee, amount, and issue date.

Phi-3-mini-128k-instruct-graph is a fine-tuned version of Microsoft's Phi-3-mini-128k-instruct, specifically designed for extracting entity relationships from general text data.

Hermes-2 Θ Llama-3 8B is a powerful model that combines the advantages of Hermes 2 Pro and Meta's Llama-3 Instruct, and performs well in various tasks. It supports multiple prompt formats and function calls.

Llama 2 is a 7B-parameter dialogue-optimized large language model developed by Meta. This version extends function calling capabilities, supporting structured JSON format responses.