|
--- |
|
license: mit |
|
datasets: |
|
- EDGEwww25/EDGE-Dataset |
|
- liuhaotian/LLaVA-Instruct-150K |
|
- echo840/Monkey_Data |
|
language: |
|
- en |
|
base_model: |
|
- echo840/Monkey-Chat |
|
--- |
|
This is the model repository of paper *EDGE: Enhanced Grounded GUI Understanding with Enriched Multi-Granularity Synthetic Data*. |
|
|
|
|
|
The model is fine-tuned based on [*Monkey*](https://github.com/Yuliang-Liu/Monkey). In order to speed up the training, we also made some minor modifications: |
|
1. Instead of using the Lora Adapters in *Monkey*, the five patches of the raw image are stacked in an extra batch dimension and sent to the image encoder for processing at the same time. |
|
2. Inside the image encoder, we use [*flash attention*](https://github.com/Dao-AILab/flash-attention) instead of the manually implemented attention. |
|
3. Separate the step of reading the image from the forward propagation and make it a step of dataset preprocessing to speed up image reading using the `Dataloader` in pytorch. |
|
|
|
|
|
The training dataset (i.e. all training QAs in `.jsonl` format, excluding images) is published in repository [*EDGE-Dataset*](https://huggingface.co/datasets/EDGEwww25/EDGE-Dataset). |
|
|
|
The model training and inference scripts are published in anonymous repository [*EDGE*](https://anonymous.4open.science/r/EDGE-1CDB). |
