# Structured JSON Output

An experimental model fine-tuned by Nous Research using the Atropos reinforcement learning framework, focused on improving the tool calling performance of the Llama-3.1 8B model in inference mode

Qwen2.5 VL 32B Instruct is a multimodal large language model developed by Qwen, supporting vision and language tasks with powerful image understanding and text generation capabilities.

fLlama 2 extends the Llama 2 model with function calling capabilities, enabling structured JSON responses that include function names and parameters. This version is trained using the GPTQ method, offering fast inference and good accuracy.