CLIP-KO-TypoAttack-Attn-Dropout-ViT-L-14

</details>

-------

# 🔥 CLIP-KO is very robust against typographis attacks, but may produce OOD Text Embeddings.
- 📝 Read the [paper](https://github.com/zer0int/CLIP-fine-tune/blob/CLIP-vision/KO-CLIP-teaser/KO-CLIP-paper-final.pdf) (PDF) here.
- 🌱 If you're looking for a a Text Encoder, you'll probably want the [KO-LITE variant](https://huggingface.co/zer0int/CLIP-KO-LITE-TypoAttack-Attn-Dropout-ViT-L-14) instead.
- Still want this one? But be warned of OOD embeddings unless you use CLEAN ENGLISH WORDS (see image examples on the bottom). This model is a nitpicker, and potentially (!) SFW (but I can't gurantee it, please see paper for details)
- ⚠️ Download the [STRICT TEXT ENCODER](https://huggingface.co/zer0int/CLIP-KO-TypoAttack-Attn-Dropout-ViT-L-14/resolve/main/ViT-L-14-KO-HuggingFace-TE-only.safetensors?download=true)
- 🤓 Wanna fine-tune yourself? Get the [code](https://github.com/zer0int/CLIP-fine-tune) on my GitHub.
- Included: Code for fine-tuning and all benchmarks / claims (as per the paper)

## 👉 Check out the [KO-LITE variant](https://huggingface.co/zer0int/CLIP-KO-LITE-TypoAttack-Attn-Dropout-ViT-L-14) of this model (less strict, but good robustness!)

----
<details>
<summary>👉 CLICK ME to expand example benchmark code ⚡💻</summary>