# Human preference alignment

Qwen3-4B is the latest large language model in the Qwen series, featuring the ability to switch thinking modes, powerful reasoning capabilities, excellent human preference alignment, outstanding agent capabilities, and multilingual support.

Qwen3-14B is the latest large language model in the Tongyi Qianwen series, with 14.8 billion parameters. It supports the switching between thinking and non-thinking modes and performs excellently in reasoning, instruction following, and intelligent agent capabilities.

Llama-VARCO-8B-Instruct is a generative model built on Llama. Through additional training, it performs excellently in Korean processing while maintaining English proficiency.

A causal language model based on Pythia-2.8b, fine-tuned using the Anthropic human preference dataset