yanggangu nielsr HF Staff commited on
Commit
c179eb5
路
1 Parent(s): 0eafc6e

Remove arXiv ID from metadata and add pipeline tag (#1)

Browse files

- Remove arXiv ID from metadata and add pipeline tag (41bd2eaa30a50aaf4ebe1d1b480e935638b26298)


Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +4 -3
README.md CHANGED
@@ -1,16 +1,17 @@
1
  ---
2
- license: mit
3
  base_model: openai/clip-vit-base-patch32
 
 
4
  tags:
5
  - smat
6
  - model-merging
7
  - vision
8
- - arxiv:2609.33437
9
  ---
 
10
  # CLIP ViT base-patch32 路 FT 路 RESISC45
11
 
12
  A FT expert from Table 2 of **SMAT: Simple and Efficient Merge-Aware Training** (seed 42). SMAT trains experts with model merging in mind.
13
 
14
  [Paper](https://arxiv.org/abs/2609.33437) 路 [GitHub & usage](https://github.com/egangu/smat/blob/main/docs/HUGGINGFACE.md)
15
 
16
- `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.
 
1
  ---
 
2
  base_model: openai/clip-vit-base-patch32
3
+ license: mit
4
+ pipeline_tag: image-classification
5
  tags:
6
  - smat
7
  - model-merging
8
  - vision
 
9
  ---
10
+
11
  # CLIP ViT base-patch32 路 FT 路 RESISC45
12
 
13
  A FT expert from Table 2 of **SMAT: Simple and Efficient Merge-Aware Training** (seed 42). SMAT trains experts with model merging in mind.
14
 
15
  [Paper](https://arxiv.org/abs/2609.33437) 路 [GitHub & usage](https://github.com/egangu/smat/blob/main/docs/HUGGINGFACE.md)
16
 
17
+ `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.