Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
zer0int
/
CLIP-SAE-ViT-L-14
like
32
Zero-Shot Image Classification
Transformers
Safetensors
zer0int/CLIP-adversarial-typographic-attack_text-image
SPRIGHT-T2I/spright_coco
clip
License:
mit
Model card
Files
Files and versions
xet
Community
3
Deploy
Use this model
main
CLIP-SAE-ViT-L-14
6.39 GB
1 contributor
History:
14 commits
zer0int
HunyuanVideo use info
7adb7b9
verified
about 1 year ago
.gitattributes
1.52 kB
initial commit
about 1 year ago
README.md
2.99 kB
HunyuanVideo use info
about 1 year ago
ViT-L-14-GmP-SAE-FULL-model.safetensors
931 MB
xet
TE-only e.g. for ComfyUI / standalone use
about 1 year ago
ViT-L-14-GmP-SAE-TE-only.safetensors
323 MB
xet
TE-only e.g. for ComfyUI / standalone use
about 1 year ago
ViT-L-14-GmP-SAE-pickle-OpenAI.pt
1.71 GB
xet
'import clip' original OpenAI format torch.save
about 1 year ago
ViT-L-14-GmP-SAE-state_dict.pt
1.71 GB
xet
'import clip' original OpenAI format torch.save
about 1 year ago
config.json
736 Bytes
SAE-informed fine-tune
about 1 year ago
merges.txt
525 kB
Upload merges.txt
about 1 year ago
model.safetensors
1.71 GB
xet
SAE-informed fine-tune
about 1 year ago
preprocessor_config.json
335 Bytes
SAE-informed fine-tune
about 1 year ago
special_tokens_map.json
389 Bytes
SAE-informed fine-tune
about 1 year ago
tokenizer.json
2.22 MB
SAE-informed fine-tune
about 1 year ago
tokenizer_config.json
902 Bytes
SAE-informed fine-tune
about 1 year ago
vocab.json
961 kB
SAE-informed fine-tune
about 1 year ago
