bokesyo commited on
Commit
e861f2a
·
1 Parent(s): e23c048

Update readme from github

Browse files
Files changed (1) hide show
  1. README.md +18 -11
README.md CHANGED
@@ -1010,23 +1010,23 @@ Advancing popular visual capabilities from MiniCPM-V series, MiniCPM-o 4.5 can p
1010
  </div>
1011
  </details>
1012
 
1013
- ### Examples: Overall <!-- omit in toc -->
 
 
1014
 
1015
  <div align="center">
1016
  <a href="https://www.youtube.com/watch?v=6UzC-O1Q-1U"><img src="https://raw.githubusercontent.com/openbmb/MiniCPM-o/main/assets/minicpmo4_5/video_play.png", width=70%></a>
1017
  </div>
1018
 
1019
- ### Examples: Omnimodal Full-Duplex Conversation <!-- omit in toc -->
1020
 
1021
  > [!NOTE]
1022
  > For detailed speech conversation examples, refer to [Omni Full-Duplex Casebook](https://openbmb.github.io/minicpm-o-4_5-omni/)
1023
 
1024
- ### Examples: 🎙️ Speech Conversation <!-- omit in toc -->
1025
 
1026
  > [!NOTE]
1027
- > For detailed speech conversation examples, refer to [Audio Demo Page](https://openbmb.github.io/minicpm-o-4_5/)
1028
-
1029
- Half-duplex speech conversation with custom reference audio and character prompts.
1030
 
1031
  <details>
1032
  <summary>🚀 <b>Elon Musk</b> - Voice Roleplay (EN)</summary>
@@ -1048,12 +1048,19 @@ Half-duplex speech conversation with custom reference audio and character prompt
1048
 
1049
  <br>
1050
 
1051
- ### Examples: Vision-Language
1052
 
1053
- <div style="display: flex; flex-direction: column; align-items: center;">
1054
- <img src="https://raw.githubusercontent.com/OpenBMB/MiniCPM-o/main/assets/minicpmo4_5/en_doc.png" alt="math" style="margin-bottom: 5px;">
1055
- <img src="https://raw.githubusercontent.com/OpenBMB/MiniCPM-o/main/assets/minicpmo4_5/en_cot.png" alt="diagram" style="margin-bottom: 5px;">
1056
- </div>
 
 
 
 
 
 
 
1057
 
1058
 
1059
  ## Offline Inference Examples with Transformers
 
1010
  </div>
1011
  </details>
1012
 
1013
+ ### Examples <!-- omit in toc -->
1014
+
1015
+ #### Overall <!-- omit in toc -->
1016
 
1017
  <div align="center">
1018
  <a href="https://www.youtube.com/watch?v=6UzC-O1Q-1U"><img src="https://raw.githubusercontent.com/openbmb/MiniCPM-o/main/assets/minicpmo4_5/video_play.png", width=70%></a>
1019
  </div>
1020
 
1021
+ #### Omnimodal Full-Duplex Conversation <!-- omit in toc -->
1022
 
1023
  > [!NOTE]
1024
  > For detailed speech conversation examples, refer to [Omni Full-Duplex Casebook](https://openbmb.github.io/minicpm-o-4_5-omni/)
1025
 
1026
+ #### Realtime Speech Conversation <!-- omit in toc -->
1027
 
1028
  > [!NOTE]
1029
+ > For detailed speech conversation examples, refer to [Audio Casebook](https://openbmb.github.io/minicpm-o-4_5/)
 
 
1030
 
1031
  <details>
1032
  <summary>🚀 <b>Elon Musk</b> - Voice Roleplay (EN)</summary>
 
1048
 
1049
  <br>
1050
 
1051
+ #### Visual Understanding <!-- omit in toc -->
1052
 
1053
+
1054
+ <details>
1055
+ <summary>Click to view visual understanding cases.</summary>
1056
+ <br>
1057
+
1058
+ <div style="display: flex; flex-direction: column; align-items: center;">
1059
+ <img src="https://raw.githubusercontent.com/OpenBMB/MiniCPM-o/main/assets/minicpmo4_5/en_doc.png" alt="math" style="margin-bottom: 5px;">
1060
+ <img src="https://raw.githubusercontent.com/OpenBMB/MiniCPM-o/main/assets/minicpmo4_5/en_cot.png" alt="diagram" style="margin-bottom: 5px;">
1061
+ </div>
1062
+
1063
+ </details>
1064
 
1065
 
1066
  ## Offline Inference Examples with Transformers