metadata
license: apache-2.0
tags:
- knowledge-distillation
- pytorch
- transformers
base_model: google/medsiglip-448
fokan/train-modle2
This model was created using knowledge distillation from the following teacher model(s):
- google/medsiglip-448
Model Description
A distilled model created using multi-modal knowledge distillation.
Training Details
- Teacher Models: google/medsiglip-448
- Distillation Strategy: ensemble
- Training Steps: 500
- Learning Rate: 0.0001
Usage
from transformers import AutoModel, AutoTokenizer
model = AutoModel.from_pretrained("fokan/train-modle2")
tokenizer = AutoTokenizer.from_pretrained("google/medsiglip-448")
Created with
This model was created using the Multi-Modal Knowledge Distillation platform.