---
datasets:
- SPRIGHT-T2I/spright_coco
---
## A fine-tune of [BeichenZhang/LongCLIP-L](https://huggingface.co/BeichenZhang/LongCLIP-L) -- Long-CLIP ViT-L/14 expanded to 248 tokens.

The fine-tune has an improved ImageNet/ObjectNet accuracy of 0.89 (original Long-CLIP by the authors:~0.81)**.


Made possible with Geometric Parametrization (GmP):

```

"Normal" CLIP MLP (multi-layer perceptron):

(mlp): Sequential(
  |-(c_fc): Linear(in_features=1024, out_features=4096, bias=True)
  | (gelu): QuickGELU()
|-}-(c_proj): Linear(in_features=4096, out_features=1024, bias=True)
| | 
| |-- visual.transformer.resblocks.0.mlp.c_fc.weight
| |-- visual.transformer.resblocks.0.mlp.c_fc.bias
|
|---- visual.transformer.resblocks.0.mlp.c_proj.weight
|---- visual.transformer.resblocks.0.mlp.c_proj.bias


GmP CLIP MLP:

Weight decomposition into:
- radial component 'r' as norm of pre-trained weights
- angular component 'theta' as normalized direction
-> preserves weight vectors' directionality and magnitude

(mlp): Sequential(
  |-(c_fc): GeometricLinear()
  | (gelu): QuickGELU()
|-}-(c_proj): GeometricLinear()
| | 
| |-- visual.transformer.resblocks.0.mlp.c_fc.r
| |-- visual.transformer.resblocks.0.mlp.c_fc.theta
| |-- visual.transformer.resblocks.0.mlp.c_fc.bias
|
|---- visual.transformer.resblocks.0.mlp.c_proj.r
|---- visual.transformer.resblocks.0.mlp.c_proj.theta
|---- visual.transformer.resblocks.0.mlp.c_proj.bias

(Same thing for [text] transformer.resblocks)

```

![image/png](https://cdn-uploads.huggingface.co/production/uploads/6490359a877fc29cb1b09451/OqhNxW-D9c58mkZyUQlL_.png)

✅ The model / state_dict I am sharing was converted back to .weight after fine-tuning - alas, it can be used in the same manner as any state_dict, e.g. for use with ComfyUI as the SDXL / SD3 Text Encoder using [SeaArtLab/ComfyUI-Long-CLIP](https://github.com/SeaArtLab/ComfyUI-Long-CLIP) custom nodes! 🤗

** For details on training and those numbers / the eval, or for just fine-tuning the model yourself, see: [https://github.com/zer0int/Long-CLIP](https://github.com/zer0int/Long-CLIP)

```
@article{zhang2024longclip,
        title={Long-CLIP: Unlocking the Long-Text Capability of CLIP},
        author={Beichen Zhang and Pan Zhang and Xiaoyi Dong and Yuhang Zang and Jiaqi Wang},
        journal={arXiv preprint arXiv:2403.15378},
        year={2024}
}
```

Pre-trained CLIP model by OpenAI, License: [MIT License](https://github.com/openai/CLIP/blob/main/LICENSE)