# Structured Output

A vision-language model specifically designed for Thai-English real-world document parsing, based on the Qwen2.5-VL-Instruction framework

Qwen2.5 is the latest series of the Qwen large language model, featuring a 1.5B parameter instruction-tuned model that supports multilingual and long text generation.

A next-generation language model based on the Qwen 2.5 14B architecture, specifically optimized for mathematical reasoning, programming, and general logical tasks.

Designed based on Qwen 2.5 14B modal architecture, enhancing coding efficiency and computational reasoning capabilities

DeepHermes 3 Preview is the latest version of Nous Research's flagship Hermes series large language models, combining reasoning and standard response modes with improved annotation, judgment, and function calling capabilities.

MiniThinky 1B is an AI assistant model fine-tuned from Llama-3.2-1B-Instruct, featuring thought process visualization before answering

Hermes 3 3B is a small yet powerful new member of the Hermes series LLMs by Nous Research, focusing on aligning LLMs with users and empowering end-users with strong guidance and control capabilities.

xLAM-7b-fc-r is a 7B-parameter large language model optimized for function calls, developed by Salesforce, capable of providing fast, accurate, and structured responses based on input queries and available APIs.

xLAM-1b-fc-r is a small-scale Large Action Model (LAM) optimized for function calls, developed by Salesforce, with 1.35B parameters, suitable for deployment on personal devices.

An improved medical dialogue model based on Llama3-8B, specifically optimized for medical Q&A and clinical text processing

Phi-3-Mini-4K-Instruct is a 3.8 billion parameter lightweight cutting-edge open-source model trained on the Phi-3 dataset, emphasizing high quality and inference-intensive characteristics.

Phi-3 Mini-4K-Instruct is a lightweight, state-of-the-art open-source model with 3.8 billion parameters, specifically emphasizing high quality and dense reasoning capabilities.

This model is fine-tuned based on meta-llama/Meta-Llama-3-8B-Instruct, specifically designed for function calling and JSON mode.

This is a spatially-aware vision-language model capable of recognizing spatial relationships between objects in images and generating descriptive text.

The YAYI-IE model is a unified large model fine-tuned with millions of manually annotated high-quality information extraction data, supporting information extraction tasks in general domains and multiple vertical domains.

FAVA is a model for verifying textual errors, capable of identifying errors in text based on reference materials and providing revision suggestions.

A biomedical domain-specific model fine-tuned with instructions based on the Llama2 7B model

An email generation model fine-tuned based on EleutherAI/gpt-neo-1.3B, excelling at generating formal or informal email content from brief prompts