Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
ModelZoo
textmonkey_pytorch
Commits
6dab4fe7
Unverified
Commit
6dab4fe7
authored
Nov 10, 2023
by
Yuliang Liu
Committed by
GitHub
Nov 10, 2023
Browse files
Update README.md
parent
a620e999
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
30 additions
and
8 deletions
+30
-8
README.md
README.md
+30
-8
No files found.
README.md
View file @
6dab4fe7
...
@@ -42,22 +42,44 @@ We have a demo open for everyone to play. [Demo](https://53965e0026f6da5097.grad
...
@@ -42,22 +42,44 @@ We have a demo open for everyone to play. [Demo](https://53965e0026f6da5097.grad
## Cases
## Cases
Our model can accurately describe
almost all
the details in the image.
Our model can accurately describe the details in the image.

<br>
<p
align=
"center"
>
<img
src=
"images/caption_1.png"
width=
"700"
/>
<p>
<br>
Besides, our model has also demonstrated some capabilities in fine-grained question answering
and even answering questions involving world knowledge
.
Besides, our model has also demonstrated some capabilities in fine-grained question answering.

<br>
<p
align=
"center"
>
<img
src=
"images/qa_1.png"
width=
"700"
/>
<p>
<br>
We have also achieved impressive performance on document-based tasks.
<br>
<p
align=
"center"
>
<img
src=
"images/Doc_Chart.png"
width=
"700"
/>
<p>
<br>
W
ith the power of large-scale architecture, we have also achieved impressive performance on document-based tasks.
W
e qualitatively compare with existing LMMs including GPT4V, Qwen-vl, etc, which shows inspiring results. One can have a try using the provided demo.

<br>
<p
align=
"center"
>
<img
src=
"images/compare.png"
width=
"800"
/>
<p>
<br>
## Acknowledgement
## Acknowledgement
[
Qwen-VL
](
https://github.com/QwenLM/Qwen-VL.git
)
: the codebase we built upon. Thanks for the authors of Qwen for providing the framework.
[
Qwen-VL
](
https://github.com/QwenLM/Qwen-VL.git
)
: the codebase we built upon. Thanks for the authors of Qwen for providing the framework.
## Copyright
For commercial purpose usage, please contact Dr. Yuliang Liu: ylliu@hust.edu.cn
## Copyright
We welcome suggestions to help us improve the little Monkey. For any query, please contact Dr. Yuliang Liu: ylliu@hust.edu.cn
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment