Update README.md
Browse files
README.md
CHANGED
@@ -12,7 +12,10 @@ tags:
|
|
12 |
# Model Card for Model ID
|
13 |
|
14 |
<!-- Provide a quick summary of what the model is/does. -->
|
15 |
-
|
|
|
|
|
|
|
16 |
|
17 |
|
18 |
## Model Details
|
@@ -32,8 +35,7 @@ This is the model card of a 🤗 transformers model that has been pushed on the
|
|
32 |
<!-- Provide the basic links for the model. -->
|
33 |
|
34 |
- **Repository:** [LlavaNext blp-4k](https://huggingface.co/chart-misinformation-detection/hf-llava-next-finetune-blp4k)(adapters only)
|
35 |
-
- **
|
36 |
-
- **Demo [optional]:** [LlavaNext BLP4k](https://huggingface.co/spaces/chart-misinformation-detection/Llava-Next-BLP4k)
|
37 |
|
38 |
## Uses
|
39 |
|
|
|
12 |
# Model Card for Model ID
|
13 |
|
14 |
<!-- Provide a quick summary of what the model is/does. -->
|
15 |
+
This is a LlavaNext model finetuned on a synthetic dataset of bar, line, and pie charts.
|
16 |
+
The goal is to detect if there is a misleading element in a chart image.
|
17 |
+
The types of misleading elements that we propose are limited to: non-zero baseline for bar charts,
|
18 |
+
omission of x-axis data points for line charts, and segments do not sum up to 100% in pie charts.
|
19 |
|
20 |
|
21 |
## Model Details
|
|
|
35 |
<!-- Provide the basic links for the model. -->
|
36 |
|
37 |
- **Repository:** [LlavaNext blp-4k](https://huggingface.co/chart-misinformation-detection/hf-llava-next-finetune-blp4k)(adapters only)
|
38 |
+
- **Demo:** [LlavaNext BLP4k](https://huggingface.co/spaces/chart-misinformation-detection/Llava-Next-BLP4k)
|
|
|
39 |
|
40 |
## Uses
|
41 |
|