Commit ·
6dfa2fd
1
Parent(s): e7809ba
release model
Browse files- .gitattributes +1 -0
- README.md +1 -1
- model.safetensors +3 -0
.gitattributes
CHANGED
|
@@ -44,3 +44,4 @@ dino_config.json filter=lfs diff=lfs merge=lfs -text
|
|
| 44 |
tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
|
| 45 |
vocab.json filter=lfs diff=lfs merge=lfs -text
|
| 46 |
*.png filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 44 |
tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
|
| 45 |
vocab.json filter=lfs diff=lfs merge=lfs -text
|
| 46 |
*.png filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
model.safetensors filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
|
@@ -51,7 +51,7 @@ This repository hosts the model weights for <b>G<sup>2</sup>VLM</b>. For install
|
|
| 51 |
|
| 52 |
|
| 53 |
## 🧠 Method
|
| 54 |
-
|
| 55 |
|
| 56 |
<p align="left"><img src="https://huggingface.co/InternRobotics/G2VLM-2B-MoT/resolve/main/assets/method.png" width="100%"></p>
|
| 57 |
|
|
|
|
| 51 |
|
| 52 |
|
| 53 |
## 🧠 Method
|
| 54 |
+
G<sup>2</sup>VLM is a unified model that integrates both a geometric perception expert for 3D reconstruction and a semantic perception expert for multimodal understanding and spatial reasoning tasks. All tokens can do shared multi-modal self attention in each transformer block.
|
| 55 |
|
| 56 |
<p align="left"><img src="https://huggingface.co/InternRobotics/G2VLM-2B-MoT/resolve/main/assets/method.png" width="100%"></p>
|
| 57 |
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b129aadea8e908b5b9036c9c56e933bd1cc587a5633701c1dda8ec0aaa122ab7
|
| 3 |
+
size 18153098992
|