EmoLLM is a series of mental health LLMs fine-tuned from instruction-tuned models to support the mental health counseling pipeline of understanding, supporting, and helping users. The project covers pre-training and post-training configurations, mental health datasets, evaluation frameworks, deployment options, and RAG integration. It supports multiple base model families including InternLM, Qwen, Baichuan, DeepSeek, Mixtral, Llama, and GLM.