| # PsyLlama: A Conversational AI for Mental Health Assessment | |
| **Model Name**: `PsyLlama` | |
| **Model Architecture**: LLaMA-based model (fine-tuned) | |
| **Model Type**: Instruct-tuned, conversational AI model | |
| **Primary Use**: Mental health assessment through psychometric analysis | |
| --- | |
| ### Model Description | |
| **PsyLlama** is a conversational AI model based on LLaMA architecture, fine-tuned for mental health assessments. It is designed to assist healthcare professionals in conducting initial psychometric evaluations and mental health assessments by generating context-aware conversational responses. The model uses structured questions and answers to assess patients' mental states and supports clinical decision-making in telemedicine environments. | |
| **Applications**: | |
| - Psychometric evaluation | |
| - Mental health chatbot | |
| - Symptom analysis for mental health assessment | |
| --- | |
| ### Model Usage | |
| To use **PsyLlama**, you can load it from Hugging Face using the `transformers` library. Below is a code snippet showing how to initialize and use the model: | |
| ```python | |
| from transformers import AutoModelForCausalLM, AutoTokenizer | |
| # Load the model and tokenizer from Hugging Face | |
| model_name = "Nevil9/PsyLlama" | |
| tokenizer = AutoTokenizer.from_pretrained(model_name) | |
| model = AutoModelForCausalLM.from_pretrained(model_name) | |
| # Example input | |
| input_text = "How are you feeling today? Have you been experiencing any anxiety or stress?" | |
| # Tokenize input and generate response | |
| inputs = tokenizer(input_text, return_tensors="pt") | |
| output = model.generate(**inputs, max_length=100) | |
| # Decode and print the response | |
| response = tokenizer.decode(output[0], skip_special_tokens=True) | |
| print(response) | |