Update README.md
Browse files
README.md
CHANGED
|
@@ -13,7 +13,7 @@ Volcano-7b was trained in October 2023.
|
|
| 13 |
**Paper or resources for more information:**
|
| 14 |
|
| 15 |
# Training dataset
|
| 16 |
-
- 274K multimodal feedback and revision data
|
| 17 |
- 558K filtered image-text pairs from LAION/CC/SBU, captioned by BLIP.
|
| 18 |
- 158K GPT-generated multimodal instruction-following data.
|
| 19 |
- 450K academic-task-oriented VQA data mixture.
|
|
@@ -22,4 +22,4 @@ Volcano-7b was trained in October 2023.
|
|
| 22 |
You can find [here](https://huggingface.co/datasets/kaist-ai/volcano-train) the dataset used to train Volcano, which includes all the aforementioned datasets.
|
| 23 |
|
| 24 |
# Evaluation dataset
|
| 25 |
-
|
|
|
|
| 13 |
**Paper or resources for more information:**
|
| 14 |
|
| 15 |
# Training dataset
|
| 16 |
+
- **274K multimodal feedback and revision data**
|
| 17 |
- 558K filtered image-text pairs from LAION/CC/SBU, captioned by BLIP.
|
| 18 |
- 158K GPT-generated multimodal instruction-following data.
|
| 19 |
- 450K academic-task-oriented VQA data mixture.
|
|
|
|
| 22 |
You can find [here](https://huggingface.co/datasets/kaist-ai/volcano-train) the dataset used to train Volcano, which includes all the aforementioned datasets.
|
| 23 |
|
| 24 |
# Evaluation dataset
|
| 25 |
+
A collection of three multimodal hallucination benchmarks ([MMHal-Bench](https://huggingface.co/datasets/Shengcao1006/MMHal-Bench), [Pope](https://github.com/RUCAIBox/POPE), [GAVIE](https://github.com/FuxiaoLiu/LRV-Instruction)) and two multimodal understanding benchmarks ([MM-Vet](https://github.com/yuweihao/MM-Vet), [MMBench](https://github.com/open-compass/MMBench)).
|