Instructions to use dattaraj/phi3-finetuned-mentalhealth 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 dattaraj/phi3-finetuned-mentalhealth 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 dattaraj/phi3-finetuned-mentalhealth # Run inference directly in the terminal: llama cli -hf dattaraj/phi3-finetuned-mentalhealth
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf dattaraj/phi3-finetuned-mentalhealth # Run inference directly in the terminal: llama cli -hf dattaraj/phi3-finetuned-mentalhealth
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 dattaraj/phi3-finetuned-mentalhealth # Run inference directly in the terminal: ./llama-cli -hf dattaraj/phi3-finetuned-mentalhealth
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 dattaraj/phi3-finetuned-mentalhealth # Run inference directly in the terminal: ./build/bin/llama-cli -hf dattaraj/phi3-finetuned-mentalhealth
Use Docker
docker model run hf.co/dattaraj/phi3-finetuned-mentalhealth
- LM Studio
- Jan
- Ollama
How to use dattaraj/phi3-finetuned-mentalhealth with Ollama:
ollama run hf.co/dattaraj/phi3-finetuned-mentalhealth
- Unsloth Desktop
- Docker Model Runner
How to use dattaraj/phi3-finetuned-mentalhealth with Docker Model Runner:
docker model run hf.co/dattaraj/phi3-finetuned-mentalhealth
- Lemonade
How to use dattaraj/phi3-finetuned-mentalhealth with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull dattaraj/phi3-finetuned-mentalhealth
Run and chat with the model
lemonade run user.phi3-finetuned-mentalhealth-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
Run and chat with the model
lemonade run user.phi3-finetuned-mentalhealth-{{QUANT_TAG}}List all available models
lemonade listYAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Model Card: Fine-tuned Phi3-mini for Mental Health FAQs
Model Details
- Model Name: Phi3-mini-MentalHealth
- Base Model: Phi3-mini
- Model Type: Language Model
- Framework: MLX
- Fine-tuning Dataset: Mental Health FAQ data from Kaggle
- Format: GGUF (GPT Quantized)
Intended Use
This model is designed to provide empathetic and informative responses to frequently asked questions about mental health. It can be used in applications such as:
- Mental health chatbots
- Educational resources about mental health
- Preliminary mental health screening tools (with appropriate disclaimers)
Training Data
The model was fine-tuned on a dataset of Mental Health FAQs from Kaggle. This dataset likely includes:
- Common questions about mental health conditions
- Basic information about symptoms and treatments
- General mental health and wellness advice
Note: The exact contents and size of the dataset should be verified and added here.
Fine-tuning Process
The Phi3-mini model was fine-tuned using the MLX framework. Specific details about the fine-tuning process, such as number of epochs, learning rate, and other hyperparameters, should be added here.
Performance and Limitations
- Improved Empathy: The fine-tuned model demonstrates increased empathy in its responses compared to the base model.
- Domain Specificity: The model's knowledge is focused on mental health topics covered in the FAQ dataset.
- Limitations:
- The model's knowledge is limited to the scope of the training data.
- It should not be used as a substitute for professional mental health advice or diagnosis.
- The model may not be up-to-date with the latest mental health research or treatments.
Ethical Considerations
- Privacy: The model should be used in ways that protect user privacy, especially given the sensitive nature of mental health discussions.
- Bias: While efforts have been made to improve empathy, the model may still exhibit biases present in the training data.
- Misuse Potential: Care should be taken to prevent the model from being used to provide medical advice it's not qualified to give.
Additional Information
- License: Apache 2.0
- Developer: Dattaraj Rao - Persistent
- Date Created: 16-Jul-2024
- Version: 1.0
For more information or to report issues, please contact: https://www.linkedin.com/in/dattarajrao/
- Downloads last month
- 5
We're not able to determine the quantization variants.
Pull the model
# Download Lemonade from https://lemonade-server.ai/