Any-to-Any
Transformers
Safetensors
gestalt
multimodal
discrete-diffusion
vision-language
unified-model
custom_code
Instructions to use GeWu-Lab/Gestalt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use GeWu-Lab/Gestalt with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import GestaltModelLM model = GestaltModelLM.from_pretrained("GeWu-Lab/Gestalt", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Theq Yang commited on
Commit ·
f8331e5
1
Parent(s): 4ce2a5f
Update paper link and model parameters
Browse files
README.md
CHANGED
|
@@ -15,7 +15,7 @@ tags:
|
|
| 15 |
|
| 16 |
<p align="center">
|
| 17 |
<a href="https://gewu-lab.github.io/Gestalt/"><img src="https://img.shields.io/badge/Gestalt-Website-0A66C2?logo=safari&logoColor=white" alt="Website"/></a>
|
| 18 |
-
<a href="https://
|
| 19 |
<a href="https://github.com/GeWu-Lab/Gestalt"><img src="https://img.shields.io/badge/Gestalt-Code-181717?logo=github" alt="Code"/></a>
|
| 20 |
<a href="https://huggingface.co/GeWuLab/Gestalt"><img src="https://img.shields.io/badge/Gestalt-Model-yellow?logo=huggingface&logoColor=yellow" alt="Model"/></a>
|
| 21 |
</p>
|
|
@@ -52,7 +52,7 @@ tags:
|
|
| 52 |
| Property | Value |
|
| 53 |
|:--|:--|
|
| 54 |
| Architecture | GestaltModelLM (discrete diffusion with interplay tokens) |
|
| 55 |
-
| Parameters |
|
| 56 |
| Hidden size | 4096 |
|
| 57 |
| Layers | 32 |
|
| 58 |
| Attention heads | 32 |
|
|
|
|
| 15 |
|
| 16 |
<p align="center">
|
| 17 |
<a href="https://gewu-lab.github.io/Gestalt/"><img src="https://img.shields.io/badge/Gestalt-Website-0A66C2?logo=safari&logoColor=white" alt="Website"/></a>
|
| 18 |
+
<a href="https://arxiv.org/pdf/2610.00576"><img src="https://img.shields.io/badge/Gestalt-Paper-red?logo=arxiv&logoColor=red" alt="Paper"/></a>
|
| 19 |
<a href="https://github.com/GeWu-Lab/Gestalt"><img src="https://img.shields.io/badge/Gestalt-Code-181717?logo=github" alt="Code"/></a>
|
| 20 |
<a href="https://huggingface.co/GeWuLab/Gestalt"><img src="https://img.shields.io/badge/Gestalt-Model-yellow?logo=huggingface&logoColor=yellow" alt="Model"/></a>
|
| 21 |
</p>
|
|
|
|
| 52 |
| Property | Value |
|
| 53 |
|:--|:--|
|
| 54 |
| Architecture | GestaltModelLM (discrete diffusion with interplay tokens) |
|
| 55 |
+
| Parameters | 8B + 0.6B |
|
| 56 |
| Hidden size | 4096 |
|
| 57 |
| Layers | 32 |
|
| 58 |
| Attention heads | 32 |
|