QuanSun commited on
Commit
70c6144
·
1 Parent(s): 72626b3
Files changed (1) hide show
  1. README.md +20 -1
README.md CHANGED
@@ -29,4 +29,23 @@ https://github.com/baaivision/EVA/tree/master/EVA-CLIP
29
  - To construct Merged-2B, we merged 1.6 billion samples from [LAION-2B](https://laion.ai/blog/laion-5b/) dataset with 0.4 billion samples from [COYO-700M](https://github.com/kakaobrain/coyo-dataset).
30
 
31
  - To our knowledge, EVA-CLIP series are the most performant open-sourced CLIP models at all scales, evaluated via zero-shot classification performance, especially on mainstream classification benchmarks such as ImageNet along with its variants.
32
- For more details about EVA-CLIP, please refer to our [paper (coming very soon)]().
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
  - To construct Merged-2B, we merged 1.6 billion samples from [LAION-2B](https://laion.ai/blog/laion-5b/) dataset with 0.4 billion samples from [COYO-700M](https://github.com/kakaobrain/coyo-dataset).
30
 
31
  - To our knowledge, EVA-CLIP series are the most performant open-sourced CLIP models at all scales, evaluated via zero-shot classification performance, especially on mainstream classification benchmarks such as ImageNet along with its variants.
32
+ For more details about EVA-CLIP, please refer to our [paper (coming very soon)]().
33
+
34
+ ### pretrained
35
+ <div align="center">
36
+
37
+ | model name | total #params | training precision | download link |
38
+ |:-----------|:------:|:------:|:------:|
39
+ | `EVA01_g_psz14` | 1.0B | `fp16` | [🤗 HF link](https://huggingface.co/QuanSun/EVA-CLIP/blob/main/EVA01_g_psz14.pt) (`2.0GB`) |
40
+ | `EVA02_B_psz14to16` | 86M | `fp16` | [🤗 HF link](https://huggingface.co/QuanSun/EVA-CLIP/blob/main/EVA02_B_psz14to16.pt) (`176MB`) |
41
+ | `EVA02_L_psz14` | 304M | `fp16` | [🤗 HF link](https://huggingface.co/QuanSun/EVA-CLIP/blob/main/EVA02_L_psz14.pt) (`609MB`) |
42
+ | `EVA02_CLIP_L_psz14_224to336` | 428M | `fp16` | [🤗 HF link](https://huggingface.co/QuanSun/EVA-CLIP/blob/main/EVA02_CLIP_L_psz14_224to336.pt) (`857MB`) |
43
+ | `EVA02_E_psz14` | 4.4B | `fp16` | [🤗 HF link](https://huggingface.co/QuanSun/EVA-CLIP/blob/main/EVA02_E_psz14.pt) (`8.7GB`) |
44
+ | `openai/clip-vit-base-patch16`| 149M | `fp16` | [🤗 HF link](https://huggingface.co/openai/clip-vit-base-patch16/blob/main/pytorch_model.bin) (`599MB`) |
45
+ | `openai/clip-vit-large-patch14`| 428M | `fp16` | [🤗 HF link](https://huggingface.co/openai/clip-vit-large-patch14/blob/main/pytorch_model.bin) (`1.7GB`) |
46
+ | `laion/CLIP-ViT-H-14-laion2B-s32B-b79K`| 1.0B | `bf16` | [🤗 HF link](https://huggingface.co/laion/CLIP-ViT-H-14-laion2B-s32B-b79K/blob/main/pytorch_model.bin) (`3.9GB`) |
47
+
48
+ </div>
49
+ EVA02_B_psz14to16 interpolates the kernel size of patch_embed from 14x14 to 16x16, and interpolate the pos_embed from 16x16 to 14x14.
50
+
51
+ EVA02_CLIP_L_psz14_224to336 interpolates the pos_embed from 16x16 to 24x24 for training EVA02_CLIP_L_336_psz14_s6B.