Instructions to use ouchni/psychologist_ai with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use ouchni/psychologist_ai with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf ouchni/psychologist_ai # Run inference directly in the terminal: llama cli -hf ouchni/psychologist_ai
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf ouchni/psychologist_ai # Run inference directly in the terminal: llama cli -hf ouchni/psychologist_ai
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf ouchni/psychologist_ai # Run inference directly in the terminal: ./llama-cli -hf ouchni/psychologist_ai
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf ouchni/psychologist_ai # Run inference directly in the terminal: ./build/bin/llama-cli -hf ouchni/psychologist_ai
Use Docker
docker model run hf.co/ouchni/psychologist_ai
- LM Studio
- Jan
- Ollama
How to use ouchni/psychologist_ai with Ollama:
ollama run hf.co/ouchni/psychologist_ai
- Unsloth Desktop
- Pi
How to use ouchni/psychologist_ai with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ouchni/psychologist_ai
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "ouchni/psychologist_ai" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use ouchni/psychologist_ai with Docker Model Runner:
docker model run hf.co/ouchni/psychologist_ai
- Lemonade
How to use ouchni/psychologist_ai with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ouchni/psychologist_ai
Run and chat with the model
lemonade run user.psychologist_ai-{{QUANT_TAG}}List all available models
lemonade list
- Hermes Agent
How to use ouchni/psychologist_ai with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ouchni/psychologist_ai
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default ouchni/psychologist_ai
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use ouchni/psychologist_ai with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ouchni/psychologist_ai
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "ouchni/psychologist_ai" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
π§ Psychologist AI β LLaMA LoRA FineβTuned Model
A conversational AI model specialized for psychological support & reflective dialogue.
π Model Overview
Psychologist AI is a fineβtuned LLaMA model designed to provide:
- Empathetic responses
- Emotionally supportive dialogue
- Reflective psychological insights
- Nonβjudgmental conversation flow
β οΈ This model does not replace certified mentalβhealth professionals.
It is intended for research, experimentation, and supportive AI applications.
ποΈ Architecture
- Base Model: LLaMA
- FineβTuning Method: LoRA (LowβRank Adaptation)
- Training Framework: Unsloth
- Format: GGUF (efficient for local inference)
- Deployable With: Ollama, llama.cpp, Python (llama-cpp-python)
π§ͺ Training Details
π― Objective
Develop a model capable of:
- empathetic listening
- emotional reflection
- soft, neutral assistance
- safe conversational behavior
π Dataset
Dialogue pairs simulating:
- therapist-style responses
- emotional support conversations
- neutral psychological guidance
No real user identities or clinical data were used.
βοΈ LoRA Training Notes
- Optimized for small GPUs
- Quantization: Q4_K_M
- Fast LoRA using Unsloth
- Supervised fine-tuning
- Safe-response prompting
π Model Files
| File | Description |
|---|---|
psychologist_ai.gguf |
Quantized GGUF model ready for inference |
Modelfile.txt |
Ollama model configuration |
π How to Use
β 1. Using Ollama
Install Ollama: https://ollama.com/download
Run the model:
ollama pull ouchni/psychologist_ai
ollama run psychologist_ai
Or create manually:
ollama create psychologist_ai -f Modelfile.txt
β 2. Using llama.cpp
./main -m psychologist_ai.gguf -p "Hi, I feel stressed and need emotional support."
β 3. Python Inference
from llama_cpp import Llama
llm = Llama(model_path="psychologist_ai.gguf")
response = llm("Hello, I'm feeling overwhelmed today.")
print(response)
β οΈ Safety & Ethical Notes
This model:
- β Should NOT be used for clinical diagnosis
- β Should NOT replace human therapists
- β Should NOT be used in crisis situations
Allowed uses:
- β Educational assistants
- β AI chat experiments
- β Empathyβfocused applications
- β Mentalβhealth awareness projects
π Performance
Optimized for:
- natural emotional tone
- safe and stable outputs
- low VRAM usage
- fast inference locally
π¨βπ» Author
Ouchni Abdelmajid
Developer & AI Engineer
Morocco
β Support the Project
If you use this model, please:
- β Star the Hugging Face model
- β Cite the repository
- β Give credit: Model by ouchni
π Links
- Model Page: https://huggingface.co/ouchni/psychologist_ai
- GitHub Project: (add your GitHub link here)
- Downloads last month
- 5
We're not able to determine the quantization variants.