Add our Huggingface address to documents (FlagAI-Open#94)

Co-authored-by: zhaohu xing <[email protected]>
Zhiyuan-Fan · Nov 11, 2022 · 0cc600c · 0cc600c
1 parent bd81dbf
commit 0cc600c
Show file tree

Hide file tree

Showing 12 changed files with 14 additions and 162 deletions.
diff --git a/examples/AltCLIP/README.md b/examples/AltCLIP/README.md
@@ -91,7 +91,7 @@ The model and weights have been open sourced on FlagAI ([https://github.com/Flag
       <td>77.3 </td>
    </tr>
    <tr>
-      <td>AlterCLIP</td>
+      <td>AltCLIP</td>
       <td>66.3 </td>
       <td>87.8 </td>
       <td>92.7 </td>
@@ -101,7 +101,7 @@ The model and weights have been open sourced on FlagAI ([https://github.com/Flag
       <td>88.3 </td>
    </tr>
    <tr>
-      <td>AlterCLIP∗</td>
+      <td>AltCLIP∗</td>
       <td>72.5 </td>
       <td>91.6 </td>
       <td>95.4 </td>
@@ -162,7 +162,7 @@ The model and weights have been open sourced on FlagAI ([https://github.com/Flag
       <td>87.9 </td>
    </tr>
    <tr>
-      <td>AlterCLIP</td>
+      <td>AltCLIP</td>
       <td>63.7 </td>
       <td>86.3 </td>
       <td>92.1 </td>
@@ -172,7 +172,7 @@ The model and weights have been open sourced on FlagAI ([https://github.com/Flag
       <td>87.2 </td>
    </tr>
    <tr>
-      <td>AlterCLIP∗</td>
+      <td>AltCLIP∗</td>
       <td>69.8 </td>
       <td>89.9 </td>
       <td>94.7 </td>
@@ -183,9 +183,10 @@ The model and weights have been open sourced on FlagAI ([https://github.com/Flag
    </tr>
 </table>
 
+![image-20221111172255521](imgs/image.png)
+
 
 
-![](imgs/imagenet.png)
 
 # 可视化效果 Visualization effects
 

diff --git a/examples/AltCLIP/imgs/image.png b/examples/AltCLIP/imgs/image.png
diff --git a/examples/AltCLIP/imgs/imagenet.png b/examples/AltCLIP/imgs/imagenet.png
diff --git a/examples/AltDiffusion/README.md b/examples/AltDiffusion/README.md
@@ -13,6 +13,12 @@ AltDiffusion 模型由名为 AltCLIP 的双语 CLIP 模型支持，该模型也
 
 注意：模型推理要求一张至少10G以上的GPU。
 
+
+
+同时，AltDiffusion的 web demo 也部署在huggingface spaces上，欢迎试用！网址为：[https://huggingface.co/spaces/BAAI/bilingual_stable_diffusion](https://huggingface.co/spaces/BAAI/bilingual_stable_diffusion)
+
+
+
 We use the pre-trained bilingual language model as our text encoder and fine-tune it using the WuDao dataset (6M) with an aesthetic score above 5.5 and the Laion data (5M) with an aesthetic score above 5.5.
 
 When fine-tuning, we use stable-diffusion v1-4 as initialization, freeze the bilingual language model, and only fine-tune the key module and vuale module of the Transformer Block in the Unet model.
@@ -23,7 +29,7 @@ AltDiffusion model is backed by a bilingual CLIP model named AltCLIP, which is a
 
 Note that the model inference requires a GPU of at least 10G above.
 
-
+Also, AltDiffusion's web demo is deployed on huggingface spaces, feel free to try it out! The web address is:[https://huggingface.co/spaces/BAAI/bilingual_stable_diffusion](https://huggingface.co/spaces/BAAI/bilingual_stable_diffusion)
 
 # 示例 Example
 

diff --git a/flagai/model/mm/clip_cn/__init__.py → flagai/model/mm/clip_guohua/__init__.py b/flagai/model/mm/clip_cn/__init__.py → flagai/model/mm/clip_guohua/__init__.py
diff --git a/flagai/model/mm/clip_cn/bert_tokenizer.py → ...ai/model/mm/clip_guohua/bert_tokenizer.py b/flagai/model/mm/clip_cn/bert_tokenizer.py → ...ai/model/mm/clip_guohua/bert_tokenizer.py
diff --git a/flagai/model/mm/clip_cn/clip.py → flagai/model/mm/clip_guohua/clip.py b/flagai/model/mm/clip_cn/clip.py → flagai/model/mm/clip_guohua/clip.py
diff --git a/...ai/model/mm/clip_cn/configuration_bert.py → ...odel/mm/clip_guohua/configuration_bert.py b/...ai/model/mm/clip_cn/configuration_bert.py → ...odel/mm/clip_guohua/configuration_bert.py
diff --git a/flagai/model/mm/clip_cn/model.py → flagai/model/mm/clip_guohua/model.py b/flagai/model/mm/clip_cn/model.py → flagai/model/mm/clip_guohua/model.py
diff --git a/flagai/model/mm/clip_cn/modeling_bert.py → flagai/model/mm/clip_guohua/modeling_bert.py b/flagai/model/mm/clip_cn/modeling_bert.py → flagai/model/mm/clip_guohua/modeling_bert.py
diff --git a/flagai/model/mm/lm/cn_clip.py → flagai/model/mm/lm/clip_guohua.py b/flagai/model/mm/lm/cn_clip.py → flagai/model/mm/lm/clip_guohua.py
@@ -1,6 +1,6 @@
 import torch
 import torch.nn as nn
-from flagai.model.mm.clip_cn.model import CLIP
+from flagai.model.mm.clip_guohua.model import CLIP
 from flagai.model.base_model import BaseModel
 
 

diff --git a/flagai/model/mm/lm/dcn_clip.py b/flagai/model/mm/lm/dcn_clip.py