|
--- |
|
tags: |
|
- transformers |
|
- xlm-roberta |
|
- eva02 |
|
- clip |
|
library_name: transformers |
|
license: cc-by-nc-4.0 |
|
--- |
|
|
|
# Jina CLIP |
|
|
|
Core implementation of Jina CLIP. The model uses: |
|
* the [EVA 02](https://github.com/baaivision/EVA/tree/master/EVA-CLIP/rei/eva_clip) architecture for the vision tower |
|
* the [Jina XLM RoBERTa with Flash Attention](https://huggingface.co/jinaai/xlm-roberta-flash-implementation) model as a text tower |
|
|
|
## Models that use this implementation |
|
|
|
- [jinaai/jina-clip-v2](https://huggingface.co/jinaai/jina-clip-v2) |
|
- [jinaai/jina-clip-v1](https://huggingface.co/jinaai/jina-clip-v1) |
|
|
|
## Requirements |
|
|
|
To use the Jina CLIP source code, the following packages are required: |
|
* `torch` |
|
* `timm` |
|
* `transformers` |
|
* `einops` |
|
* `xformers` to use x-attention |
|
* `flash-attn` to use flash attention |
|
* `apex` to use fused layer normalization |
|
|
