|
|
--- |
|
|
library_name: transformers |
|
|
tags: |
|
|
- unsloth |
|
|
--- |
|
|
|
|
|
# Model Card for LLAMA-DISEASE-CURE |
|
|
|
|
|
<!-- Provide a quick summary of what the model is/does. --> |
|
|
|
|
|
`LLAMA-DISEASE-CURE` is a fine-tuned version of the LLaMA-3 8B model optimized for disease classification and suggesting potential cures based on patient textual input. This model helps automate the mapping of symptoms to diseases and treatment strategies, enabling applications in AI-powered clinical decision support tools. |
|
|
|
|
|
## Model Details |
|
|
|
|
|
### Model Description |
|
|
|
|
|
<!-- Provide a longer summary of what this model is. --> |
|
|
|
|
|
This is the model card of a 🤗 Transformers model pushed to the Hub by Kshitij Sharma. It has been fine-tuned using Unsloth’s efficient low-bit training (4-bit quantization) on a medical dataset containing patient symptoms and corresponding diseases with treatments. |
|
|
|
|
|
- **Developed by:** Kshitij Sharma |
|
|
- **Funded by [optional]:** Self-funded |
|
|
- **Shared by [optional]:** Kshitij Sharma |
|
|
- **Model type:** Text Classification (Medical NLP) |
|
|
- **Language(s) (NLP):** English |
|
|
- **License:** Apache 2.0 |
|
|
- **Finetuned from model [optional]:** unsloth/llama-3-8b-bnb-4bit |
|
|
|
|
|
### Model Sources [optional] |
|
|
|
|
|
<!-- Provide the basic links for the model. --> |
|
|
|
|
|
- **Repository:** [https://huggingface.co/kshitij230/LLAMA-DISEASE-CURE](https://huggingface.co/kshitij230/LLAMA-DISEASE-CURE) |
|
|
- **Paper [optional]:** N/A |
|
|
- **Demo [optional]:** Coming soon |
|
|
|
|
|
## Uses |
|
|
|
|
|
### Direct Use |
|
|
|
|
|
- Text classification of patient-reported symptoms into disease categories |
|
|
- Generation of suggested cures or treatments based on classified disease |
|
|
|
|
|
### Downstream Use [optional] |
|
|
|
|
|
- Integration into clinical assistants or triage bots |
|
|
- Medical report preprocessing or symptom understanding tools |
|
|
- Telemedicine AI assistant solutions |
|
|
|
|
|
### Out-of-Scope Use |
|
|
|
|
|
- Should not be used for critical, real-time medical diagnosis |
|
|
- Not a substitute for licensed medical professionals |
|
|
- Should not be used in emergencies or for prescribing medication |
|
|
|
|
|
## Bias, Risks, and Limitations |
|
|
|
|
|
- Limited by the coverage and quality of the dataset used |
|
|
- May not generalize well to rare diseases or symptoms expressed in colloquial terms |
|
|
- May contain biases present in training data (e.g., demographic or linguistic) |
|
|
|
|
|
### Recommendations |
|
|
|
|
|
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. It is recommended that all outputs are reviewed by qualified healthcare professionals before clinical use. |
|
|
|
|
|
## How to Get Started with the Model |
|
|
|
|
|
Use the code below to get started with the model. |
|
|
|
|
|
```python |
|
|
from transformers import pipeline |
|
|
|
|
|
classifier = pipeline("text-classification", model="kshitij230/LLAMA-DISEASE-CURE") |
|
|
output = classifier("Patient reports shortness of breath, chest pain, and dizziness.") |
|
|
print(output) |
|
|
|
