EmoLLM - Large Language Model for Mental Health

August 19, 2025 · View on GitHub

EmoLLM - Large Language Model for Mental Health

Logo

Contributors Forks Issues OpenXLab_App OpenXLab_Model MIT License Stargazers

EmoLLM

简体中文 | English | 日本語

Explore the documentation of this project »

EmoLLM 2.0 Demo · Report a Bug · Propose a New Feature

EmoLLM is a series of large language models designed to understand, support and help customers in mental health counseling. It is fine-tuned from the LLM instructions. We really appreciate it if you could give it a star~⭐⭐. The open-sourced configuration is as follows:

ModelTypeFile LinksModel Links
Deepseek-R1_14b_int4QLoRAunslothModelScope
InternLM2_5_7B_chatfull fine-tuninginternlm2_5_chat_7b_full.pyOpenXLab, ModelScope
InternLM2_5_7B_chatQLoRAinternlm2_5_chat_7b_qlora_oasst1_e3.pyModelScope
InternLM2_7B_chatQLoRAinternlm2_7b_chat_qlora_e3.pyModelScope
InternLM2_7B_chatfull fine-tuninginternlm2_chat_7b_full.pyOpenXLab
InternLM2_7B_baseQLoRAinternlm2_7b_base_qlora_e10_M_1e4_32_64.pyOpenXLab, ModelScope
InternLM2_1_8B_chatfull fine-tuninginternlm2_1_8b_full_alpaca_e3.pyOpenXLab, ModelScope
InternLM2_20B_chatLoRAinternlm2_20b_chat_lora_alpaca_e3.py
Qwen_7b_chatQLoRAqwen_7b_chat_qlora_e3.py
Qwen1_5-0_5B-Chatfull fine-tuningqwen1_5_0_5_B_full.pyModelScope
Baichuan2_13B_chatQLoRAbaichuan2_13b_chat_qlora_alpaca_e3.py
ChatGLM3_6BLoRAchatglm3_6b_lora_alpaca_e3.py
DeepSeek MoE_16B_chatQLoRAdeepseek_moe_16b_chat_qlora_oasst1_e3.py
Mixtral 8x7B_instructQLoRAmixtral_8x7b_instruct_qlora_oasst1_e3.py
LLaMA3_8b_instructQLoRAaiwei_llama3_8b_instruct_qlora_e3.pyOpenXLab, ModelScope
LLaMA3_8b_instructQLoRAllama3_8b_instruct_qlora_alpaca_e3_M_ruozhi_scM.pyOpenXLab, ModelScope
Qwen2-7B-InstructLoRAQwen2-7B-Instruct_lora.pyModelScope
……………………

🎉 Everyone is welcome to contribute to this project!

🔍 Those who are interested in the principles and underlying implementations of LLMs can follow ThinkLLM, which focuses on building various components of large models from scratch.

The Model aims to fully understand and promote the mental health of individuals, groups, and society. This model typically includes the following key components:

  • Cognitive factors: Involving an individual's thought patterns, belief systems, cognitive biases, and problem-solving abilities. Cognitive factors significantly impact mental health as they affect how individuals interpret and respond to life events.
  • Emotional factors: Including emotion regulation, emotional expression, and emotional experiences. Emotional health is a crucial part of mental health, involving how individuals manage and express their emotions and how they recover from negative emotions.
  • Behavioral factors: Concerning an individual's behavior patterns, habits, and coping strategies. This includes stress management skills, social skills, and self-efficacy, which is the confidence in one's abilities.
  • Social environment: Comprising external factors such as family, work, community, and cultural background, which have direct and indirect impacts on an individual's mental health.
  • Physical health: There is a close relationship between physical and mental health. Good physical health can promote mental health and vice versa.
  • Psychological resilience: Refers to an individual's ability to recover from adversity and adapt. Those with strong psychological resilience can bounce back from challenges and learn and grow from them.
  • Prevention and intervention measures: The Mental Health Grand Model also includes strategies for preventing psychological issues and promoting mental health, such as psychological education, counseling, therapy, and social support systems.
  • Assessment and diagnostic tools: Effective promotion of mental health requires scientific tools to assess individuals' psychological states and diagnose potential psychological issues.
占位图 占位图
占位图 占位图
占位图

Recent Updates

View More

模型下载量

  • [2024.02.05] The project has been promoted by the official WeChat account NLP Engineering. Here's the link to the article. Welcome everyone to follow!! 🥳🥳

公众号二维码

Honors

  • The project won the the Innovation and Creativity Award in the 2024 Puyuan Large Model Series Challenge Spring Competition held by the Shanghai Artificial Intelligence Laboratory

Challenge Innovation and Creativity Award

Roadmap

Roadmap_EN

Contents

Pre-development Configuration Requirements.
  • A100 40G (specifically for InternLM2_7B_chat + qlora fine-tuning + deepspeed zero2 optimization)
  • [TODO]: Publish more details about hardware consumption.
User Guide
  1. Clone the repo
git clone https://github.com/SmartFlowAI/EmoLLM.git
  1. Read in sequence or read sections you're interested in：

🍪Quick start

📌Data Construction

🎨Incremental Pre-training and Fine-tuning Guide

🔧Deployment Guide

⚙RAG (Retrieval Augmented Generation)

🎓Evaluation Guide

  • The model evaluation is divided into General Metrics Evaluation and Professional Metrics Evaluation，Please read the evaluation guide for reference.
Additional Details

Frameworks Used

How to participate in this project

Contributions make the open-source community an excellent place for learning, inspiration, and creation. Any contribution you make is greatly appreciated.

  1. Fork the Project
  2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
  3. Commit your Changes (git commit -m 'Add some AmazingFeature')
  4. Push to the Branch (git push origin feature/AmazingFeature)
  5. Open a Pull Request

Version control

This project uses Git for version control. You can see the currently available versions in the repository.

Authors (in no particular order)

UsernameSchool/OrganizationRemarksContributions
aJupyterNankai University, Master's studentDataWhale memberProject initiator
MING-ZCHHuazhong University of Science and Technology, Undergraduate studentLLM X Mental health researcherProject co-leader
chg0901Ph.D Student of Kwangwoon University in South KoreaMiniSoraProject co-leader
jujimeizuoJiangnan University, Master's student
Smiling-Weeping-zhrHarbin Institute of Technology (Weihai), Undergraduate student
8baby8PaddlePaddle Pilot Team Regional DirectorWenxin Large Model core developer
zxazysNankai University, Master's student
JasonLLLLLLLLLLLSWUFE (Southwestern University of Finance and Economics)
MrCatAIAI Mover
ZeyuBaInstitute of Automation, Master's student
aiyinyuedejustinUniversity of Pennsylvania, Master's student
Nobody-MLChina University of Petroleum (East China), Undergraduate student
MxoderBeihang University, Undergraduate student
AnooymanNanjing University of Science and Technology, Master's student
Vicky-3021Xidian University, Master's student (Research Year 0)
SantiagoTOPTaiyuan University of Technology, Master's studentData cleansing, document management, Baby EmoLLM maintenance
zealot52099Individual developerData Processing, LLM finetuning and RAG
wwwyfffFuDan University, Master's student
jkhumorNankai University, Master's studentRAG
lll997150986Nankai University, Master's studentFine Tuning
nln-makerNankai University, Master's studentFront-end and back-end development
dream00001Nankai University, Master's studentFront-end and back-end development
王几行XINGPeking University, Master's graduateData Processing, LLM finetuning, Front-end and back-end development
[思在]Peking University, Master's graduate (Microsoft)LLM finetuning, Front-end and back-end development
TingWeiUniversity Of Electronic Science And Technology Of China,Master's graduateLLM finetuning
PengYuShihezi University, Master's studentLLM finetuning
KedreamixShenzhen University, Master’s studentThe First Mental Health R1 Distillation Dataset
HaiyangPengAI Algorithm EngineerDeveloped AI Psychological Assistant-Deep Thinking Version

The project is licensed under the MIT License. Please refer to the details LICENSE

Citation

If this project is helpful in your work, please use the following citation format:

@misc{2024EmoLLM,
    title={EmoLLM: Reinventing Mental Health Support with Large Language Models},
    author={EmoLLM Team},
    howpublished={\url{https://github.com/SmartFlowAI/EmoLLM}},
    year={2024}
}

Work list

A non-exhaustive list of works citing EmoLLM is provided below. The order of appearance does not imply ranking. Contributions to this list are welcome.

  • Yin C, Li F, Zhang S, et al. Mdd-5k: A new diagnostic conversation dataset for mental disorders synthesized via neuro-symbolic llm agents[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2025, 39(24): 25715-25723.
  • Gu Q, Li S, Zheng T, et al. Steel-LLM: From Scratch to Open Source--A Personal Journey in Building a Chinese-Centric LLM[J]. arXiv preprint arXiv:2502.06635, 2025.
  • Dai C, Hu J, Shi H, et al. Psyche-R1: Towards Reliable Psychological LLMs through Unified Empathy, Expertise, and Reasoning[J]. arXiv preprint arXiv:2508.10848, 2025.
  • Wang M, Wang P, Wu L, et al. AnnaAgent: Dynamic Evolution Agent System with Multi-Session Memory for Realistic Seeker Simulation[J]. arXiv preprint arXiv:2506.00551, 2025.
  • Feng Y, Wang Q, Liu K, et al. AI PsyRoom: Artificial Intelligence Platform for Segmented Yearning and Reactive Outcome Optimization Method[J]. arXiv preprint arXiv:2506.06740, 2025.

Acknowledgments

People

⚠️ Disclaimer

All source code and models in this repository are open-sourced under the MIT license. The currently released EmoLLM model has certain limitations, and we make the following statement:

EmoLLM is designed to provide emotional support and related advice only; it does not offer professional psychological counseling or therapy services. EmoLLM is not a substitute for licensed psychologists or therapists, and it may have inherent limitations, potentially generating incorrect, harmful, offensive, or otherwise undesirable outputs. Users should exercise caution in critical or high-risk scenarios and refrain from relying on EmoLLM’s outputs as the sole basis for decisions to avoid personal harm, property damage, or other significant losses.

Under no circumstances shall the authors, contributors, or copyright holders be liable for any claims, damages, or other liabilities arising from the use of EmoLLM or transactions involving the software, whether based on contract, tort, or other legal grounds.

By using EmoLLM, you agree to these terms and conditions and acknowledge the potential risks associated with its use. You also agree to indemnify and hold the authors, contributors, and copyright holders harmless from any claims, damages, or liabilities resulting from your use of EmoLLM.

Star History

Star History Chart

🌟 Contributors

EmoLLM contributors

Communication group

  • If it fails, go to the Issue section.

EmoLLM official communication group