|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- BI55/MedText |
|
language: |
|
- en |
|
library_name: transformers |
|
pipeline_tag: text-generation |
|
tags: |
|
- medical |
|
--- |
|
# Model Card for Phi-Med-V1 |
|
|
|
<!-- Provide a quick summary of what the model is/does. --> |
|
|
|
Microsoft Phi2 Finetuned on Medical Text Data |
|
|
|
## Model Details |
|
|
|
### Model Description |
|
|
|
<!-- Provide a longer summary of what this model is. --> |
|
|
|
|
|
|
|
- **Developed by:** [JJ] |
|
- **Model type:** [SLM] |
|
- **Finetuned from model:** [microsoft/Phi-2] |
|
|
|
|
|
## 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. --> |
|
|
|
Testing the effectivness of Finetuning SLMs |
|
|
|
### Direct Use |
|
|
|
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> |
|
|
|
Not Allowed as this is for research only |
|
|
|
|
|
|
|
|
|
## Bias, Risks, and Limitations |
|
|
|
<!-- This section is meant to convey both technical and sociotechnical limitations. --> |
|
|
|
Model can still Halucinate. |
|
|
|
|
|
## 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. --> |
|
|
|
MedText Dataset from HuggingFace |
|
|
|
### Training Procedure |
|
|
|
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> |
|
|
|
SFT using HF Transformers |
|
|
|
|
|
## Environmental Impact |
|
|
|
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> |
|
|
|
- **Hardware Type:** A10 GPU VMs [2x24GB A10] |
|
- **Hours used:** [3] |
|
- **Cloud Provider:** [Azure] |
|
- **Compute Region:** [North Europe (Dublin)] |
|
|
|
- Experiments were conducted using Azure in region northeurope, which has a carbon efficiency of 0.62 kgCO$_2$eq/kWh. A cumulative of 100 hours of computation was performed on hardware of type A10 (TDP of 350W). |
|
|
|
- Total emissions are estimated to be 21.7 kgCO$_2$eq of which 100 percents were directly offset by the cloud provider. |
|
|
|
- Estimations were conducted using the [https://mlco2.github.io/impact#compute][MachineLearning Impact calculator] |
|
|
|
|
|
## Technical Specifications [optional] |
|
|
|
|
|
### Compute Infrastructure |
|
|
|
[Azure] |
|
|
|
#### Hardware |
|
|
|
[NV72ads A10 GPU VMs] |
|
|
|
#### Software |
|
|
|
[Axolotl] |
|
|
|
## Model Card Authors [optional] |
|
|
|
[JJ] |
|
|
|
## Model Card Contact |
|
|
|
[JJ] |
|
|
|
|
|
|
