Model Card for Phi-Med-V1

Microsoft Phi2 Finetuned on Medical Text Data

Model Details

Model Description

• Developed by: [JJ]
• Model type: [SLM]
• Finetuned from model: [microsoft/Phi-2]

Uses

Testing the effectivness of Finetuning SLMs

Direct Use

Not Allowed as this is for research only

Bias, Risks, and Limitations

Model can still Halucinate.

Training Details

Training Data

MedText Dataset from HuggingFace

Training Procedure

SFT using HF Transformers

Environmental Impact

• 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]