Update README.md
Browse files
README.md
CHANGED
|
@@ -16,6 +16,9 @@ We present the first RL-trained chart-specific explainable model with SOTA perfo
|
|
| 16 |
The model is trained to predict chart type, data table, CoT reasoning and the final answer.
|
| 17 |
Note this model is trained on curated chart data on reasoning.
|
| 18 |
|
|
|
|
|
|
|
|
|
|
| 19 |
# Chart-RVR Inference Demo
|
| 20 |
|
| 21 |
This script demonstrates how to use the [`sanchit97/chart-rvr-hard-3b`](https://huggingface.co/sanchit97/chart-rvr-hard-3b) model for chart-based reasoning using a vision-language interface. It loads a chart image from a URL, prompts the model with a question, and extracts the structured reasoning and final answer.
|
|
|
|
| 16 |
The model is trained to predict chart type, data table, CoT reasoning and the final answer.
|
| 17 |
Note this model is trained on curated chart data on reasoning.
|
| 18 |
|
| 19 |
+
Code to train this model is available [here](https://github.com/sanchit97/chartrl)
|
| 20 |
+
Dataset is available [here](https://huggingface.co/datasets/sanchit97/chart-rvr-grpo-train)
|
| 21 |
+
|
| 22 |
# Chart-RVR Inference Demo
|
| 23 |
|
| 24 |
This script demonstrates how to use the [`sanchit97/chart-rvr-hard-3b`](https://huggingface.co/sanchit97/chart-rvr-hard-3b) model for chart-based reasoning using a vision-language interface. It loads a chart image from a URL, prompts the model with a question, and extracts the structured reasoning and final answer.
|