Downloads · 30 days
17
11% of all-time downloads
EDGE-Model
EDGEwww25/EDGE-Model
EDGE-Model is a machine learning model from EDGEwww25. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
This is the model repository of paper EDGE: Enhanced Grounded GUI Understanding with Enriched Multi-Granularity Synthetic Data.
All-time downloads
151
Public
Repo size
19.3 GB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.bin19.3 GB · 100%
At a glance
- License
- mit
- Model type
- monkey
- Access
- Public
- Created
- Oct 19, 2024
- Updated
- Oct 19, 2024
- SHA
- 3f912245
Base models
Model card
From the Hugging Face model README
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. In order to speed up the training, we also made some minor modifications:
- 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.
- Inside the image encoder, we use flash attention instead of the manually implemented attention.
- 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
Dataloaderin pytorch.
The training dataset (i.e. all training QAs in .jsonl format, excluding images) is published in repository EDGE-Dataset.
The model training and inference scripts are published in anonymous repository EDGE.
- Type
- monkey
- License
- mit
- Languages
- en
- Created
- Oct 19, 2024
- Updated
- Oct 19, 2024