# SmartFlowAI/EmoLLM

心理健康大模型 (LLM x Mental Health), Pre & Post-training & Dataset & Evaluation & Depoly & RAG,  with InternLM / Qwen / Baichuan / DeepSeek / Mixtral / LLama / GLM series models

Repository: https://github.com/SmartFlowAI/EmoLLM
Canonical: https://ross.abutalabs.com/products/emollm
Homepage: https://openxlab.org.cn/apps/detail/chg0901/EmoLLMV3.0
Language: Python
License: MIT
License Family: permissive
Topics: llm, the-big-model-of-mental-health, dataset, depoly, evaluation, post-training
Last push: 2026-06-18T16:47:43+00:00

## Health v2 (maintenance only)
Score: 59/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 88, release rhythm 16, longevity 68
- inputs: {"age_days": 965, "days_push": 76, "days_rel": 472, "gap_med": 104.0, "n_releases_24m": 3}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1780, forks 224 (observed 2026-08-28T04:05:35.372739+00:00)

## What it is
EmoLLM is a series of open-source large language models fine-tuned for mental health understanding and support, built on models like InternLM, Qwen, DeepSeek, and others. It includes training configurations, datasets, evaluation, RAG, and deployment tooling for psychological counseling assistants.

## Use cases
- fine-tune an llm for mental health counseling
- build a psychological support chatbot
- find mental health training datasets for llms
- deploy a mental health assistant model
- evaluate llm performance on counseling tasks
- add rag to a therapy chatbot

## When to choose
- you need an open-source LLM specialized in mental health support
- you want full training, dataset, evaluation, and deployment recipes in one project
- you work with Chinese-language psychological counseling data

## When to avoid
- you need a clinically certified or production medical device
- you only need a general-purpose chatbot without mental health focus
- you cannot run GPU-based model training or inference

## Facets
- artifact type: library
- maturity: active
- function: llm-training, rag, chatbot, machine-learning, data-generation
- domain: large-language-models, healthcare, artificial-intelligence
- platform: python, self-hosted
- tags: mental-health, fine-tuning, qlora, chinese-llm, psychological-support, xtuner, internlm, qwen, natural-language-processing, gpu

## Member repositories
- SmartFlowAI/EmoLLM (main) score 59

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:35.372739+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:24:33.116057+00:00, confidence not recorded.
  - readme: https://github.com/SmartFlowAI/EmoLLM (fetched 2026-08-28T04:05:35.372739+00:00, sha d072a8dffae7)
  - homepage: https://openxlab.org.cn/apps/detail/chg0901/EmoLLMV3.0 (fetched 2026-08-29T11:03:09.377636+00:00, sha 39ac88edc400)
- Data as of 2026-08-30T08:39:29.467469+00:00.