96 lines
3.2 KiB
Markdown
96 lines
3.2 KiB
Markdown
---
|
||
license: apache-2.0
|
||
datasets:
|
||
- Amod/mental_health_counseling_conversations
|
||
- ZahrizhalAli/mental_health_conversational_dataset
|
||
language:
|
||
- en
|
||
metrics:
|
||
- bertscore
|
||
base_model:
|
||
- Qwen/Qwen2.5-0.5B-Instruct
|
||
pipeline_tag: text2text-generation
|
||
|
||
---
|
||
|
||
|
||
# Model Overview
|
||
|
||
HealthModel_Qwen2.5-0.5B-Instruct is a fine-tuned version of Qwen/Qwen2.5-0.5B-Instruct, specifically trained to provide supportive and informative responses for mental health counseling conversations. This model is designed to assist users in seeking advice, coping strategies, and general guidance on mental well-being.
|
||
|
||
## Fine-Tuning Details
|
||
|
||
This model has been further fine-tuned on the following datasets:
|
||
|
||
Amod/Mental Health Counseling Conversations: A dataset containing counseling conversations designed to support individuals struggling with mental health issues.
|
||
|
||
ZahrizhalAli/Mental Health Conversational Dataset: A dataset featuring mental health-related dialogues, aimed at enhancing conversational AI models for mental health support.
|
||
|
||
|
||
## Model Usage
|
||
|
||
Loading the Model
|
||
|
||
To use the model, install transformers and torch if you haven’t already:
|
||
|
||
```sh
|
||
pip install transformers torch
|
||
|
||
Then, load the model and tokenizer:
|
||
|
||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||
|
||
tokenizer = AutoTokenizer.from_pretrained("your-hf-username/HealthModel_Qwen2.5-0.5B-Instruct")
|
||
model = AutoModelForCausalLM.from_pretrained("your-hf-username/HealthModel_Qwen2.5-0.5B-Instruct")
|
||
```
|
||
|
||
Generating Responses
|
||
|
||
You can generate mental health counseling responses using:
|
||
|
||
messages = [
|
||
{"role": "system", "content": "You are a mental health counseling conversations agent, supporting and advising users on mental well-being."},
|
||
{"role": "user", "content": "I'm feeling very anxious lately. What can I do?"}
|
||
]
|
||
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||
|
||
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
||
generated_ids = model.generate(**model_inputs, max_new_tokens=512)
|
||
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
||
print(response)
|
||
|
||
Intended Use
|
||
|
||
This model is intended for research and mental health support applications. It can assist in providing general advice but is not a substitute for professional therapy. Users experiencing severe mental health issues should consult a licensed professional.
|
||
|
||
Limitations & Ethical Considerations
|
||
|
||
The model may not always provide accurate or appropriate advice for severe mental health concerns.
|
||
|
||
The responses are generated based on training data and may not fully reflect human-like empathy and understanding.
|
||
|
||
Users should verify critical advice with qualified professionals.
|
||
|
||
Acknowledgments
|
||
|
||
Special thanks to the creators of the datasets used in fine-tuning:
|
||
|
||
Amod
|
||
|
||
ZahrizhalAli
|
||
|
||
License
|
||
|
||
This model is released under the same licensing terms as the original Qwen2.5-0.5B-Instruct. Please refer to the original license for details.
|
||
|
||
Citation
|
||
|
||
If you use this model, please cite:
|
||
|
||
@misc{HealthModel_Qwen2.5,
|
||
author = {Your Name or Organization},
|
||
title = {HealthModel_Qwen2.5-0.5B-Instruct},
|
||
year = {2025},
|
||
publisher = {Hugging Face},
|
||
url = {https://huggingface.co/your-hf-username/HealthModel_Qwen2.5-0.5B-Instruct}
|
||
} |