|
--- |
|
license: llama3.2 |
|
tags: |
|
- unsloth |
|
- text-generation |
|
datasets: |
|
- marmikpandya/mental-health |
|
- Amod/mental_health_counseling_conversations |
|
- AdithyaSK/CompanionLLama_instruction_30k |
|
base_model: |
|
- unsloth/Llama-3.2-3B-Instruct |
|
library_name: transformers |
|
|
|
--- |
|
# Model Card for Model ID |
|
|
|
<!-- Provide a quick summary of what the model is/does. --> |
|
|
|
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1). |
|
|
|
## Model Details |
|
|
|
### Model Description |
|
|
|
<!-- Provide a longer summary of what this model is. --> |
|
This model has been fine-tuned for use in a chatbot aimed at mental well-being support. It is designed to offer empathetic, supportive responses to users' mental health inquiries. A combined dataset was created by merging three relevant datasets for training to enhance the model’s ability to understand and respond appropriately in counseling scenarios. |
|
|
|
- **Model Name:** Llama_finetunedModel |
|
- **Developed by:** Ayesha Noor |
|
- **Model type:** Language model for conversational AI |
|
- **Language(s) (NLP):** English |
|
- **Finetuned model:** https://huggingface.co/ayeshaNoor1/Llama_finetunedModel |
|
|
|
### Model Sources |
|
|
|
<!-- Provide the basic links for the model. --> |
|
|
|
- **Repository:** https://huggingface.co/ayeshaNoor1 |
|
|
|
## Uses |
|
|
|
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> |
|
|
|
### Direct Use |
|
|
|
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> |
|
|
|
Intended for mental health chatbot applications, particularly for providing initial support, resources, and empathetic responses in mental well-being conversations. |
|
|
|
### Downstream Use |
|
|
|
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> |
|
|
|
May be used as part of broader mental health support applications, integrated into platforms aimed at user well-being. |
|
|
|
### Out-of-Scope Use |
|
|
|
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> |
|
|
|
Not recommended for critical mental health assessments, as it is not a replacement for professional help. Avoid using for high-stakes decision-making without appropriate oversight. |
|
|
|
|
|
### Recommendations |
|
|
|
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> |
|
|
|
Users should be aware of the limitations in handling diverse mental health needs and sensitive conversations. Professional oversight is advised when using in serious or emergency mental health contexts. |
|
|
|
|
|
## How to Get Started with the Model |
|
|
|
Use the code below to get started with the model. |
|
|
|
```python |
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
|
tokenizer = AutoTokenizer.from_pretrained("ayeshaNoor1/Llama_finetunedModel") |
|
model = AutoModelForCausalLM.from_pretrained("ayeshaNoor1/Llama_finetunedModel") |
|
|
|
# Sample input text |
|
input_text = "I'm feeling really down lately. Can you help me?" |
|
|
|
# Tokenize and generate response |
|
inputs = tokenizer(input_text, return_tensors="pt") |
|
outputs = model.generate(**inputs) |
|
|
|
# Decode and print the response |
|
response = tokenizer.decode(outputs[0], skip_special_tokens=True) |
|
print(response) |
|
|
|
``` |
|
|
|
## Training Details |
|
|
|
### Training Data |
|
|
|
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> |
|
A single dataset was created by merging: |
|
|
|
- **First Dataset:** - https://huggingface.co/datasets/marmikpandya/mental-health |
|
- **Second Dataset:** - https://huggingface.co/datasets/Amod/mental_health_counseling_conversations |
|
- **Third Dataset:** - https://huggingface.co/datasets/AdithyaSK/CompanionLLama_instruction_30k |
|
|
|
### Training Procedure |
|
|
|
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> |
|
|
|
#### Preprocessing |
|
|
|
Data was preprocessed to ensure consistency in format, relevance to mental health support, and removal of any sensitive or personal identifiers. |
|
|
|
#### Summary |
|
The model demonstrated proficiency in providing supportive responses in well-being conversations. |
|
|
|
|
|
## Technical Specifications |
|
|
|
|
|
### Compute Infrastructure |
|
|
|
#### Software |
|
|
|
- **Libraries:** transformers, datasets, torch, pandas, trl, unsloth |
|
- **Framework:** PyTorch |
|
|
