SMAT: Simple and Efficient Merge-Aware Training
Collection
Paper, FT/SMAT experts and frozen datasets for Tables 1 and 2. • 63 items • Updated
CLIP ViT large-patch14 · FT · MNIST
A FT expert from Table 2 of SMAT: Simple and Efficient Merge-Aware Training (seed 42). SMAT trains experts with model merging in mind.
encoder.pt is the original FP32 vision-encoder state dictionary; load it with the SMAT code and the matching OpenAI CLIP base model. Dataset terms apply separately.
Model tree for yanggangu/CLIP-ViT-large-patch14-FT-MNIST
Base model
openai/clip-vit-large-patch14