Hugging Face's logo

yanggangu
/
CLIP-ViT-base-patch32-FT-MNIST

Image Classification
smat
model-merging
vision
Model card Files
xet
 Community
1
CLIP-ViT-base-patch32-FT-MNIST / README.md
yanggangu's picture
yanggangu
Remove arXiv tag from metadata, add pipeline tag (#1)
2de028a
preview code
|
Raw History Blame Contribute Delete
607 Bytes
metadata 
base_model: openai/clip-vit-base-patch32
license: mit
pipeline_tag: image-classification
tags:
  - smat
  - model-merging
  - vision

CLIP ViT base-patch32 路 FT 路 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.

Paper 路 GitHub & usage

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.