Commit
•
f7c59d4
1
Parent(s):
97b8dce
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
inference: false
|
3 |
+
---
|
4 |
+
|
5 |
+
<br>
|
6 |
+
<br>
|
7 |
+
|
8 |
+
# LLaVA Model Card
|
9 |
+
|
10 |
+
## Model details
|
11 |
+
|
12 |
+
**Model type:**
|
13 |
+
LLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data.
|
14 |
+
It is an auto-regressive language model, based on the transformer architecture.
|
15 |
+
|
16 |
+
**Model date:**
|
17 |
+
LLaVA-LLaMA-2-13B-Chat-Preview was trained in July 2023.
|
18 |
+
|
19 |
+
**Paper or resources for more information:**
|
20 |
+
https://llava-vl.github.io/
|
21 |
+
|
22 |
+
## License
|
23 |
+
Llama 2 is licensed under the LLAMA 2 Community License,
|
24 |
+
Copyright (c) Meta Platforms, Inc. All Rights Reserved.
|
25 |
+
|
26 |
+
**Where to send questions or comments about the model:**
|
27 |
+
https://github.com/haotian-liu/LLaVA/issues
|
28 |
+
|
29 |
+
## Intended use
|
30 |
+
**Primary intended uses:**
|
31 |
+
The primary use of LLaVA is research on large multimodal models and chatbots.
|
32 |
+
|
33 |
+
**Primary intended users:**
|
34 |
+
The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.
|
35 |
+
|
36 |
+
## Training dataset
|
37 |
+
- 558K filtered image-text pairs from LAION/CC/SBU, captioned by BLIP.
|
38 |
+
- 80K GPT-generated multimodal instruction-following data.
|
39 |
+
|
40 |
+
## Evaluation dataset
|
41 |
+
A preliminary evaluation of the model quality is conducted by creating a set of 90 visual reasoning questions from 30 unique images randomly sampled from COCO val 2014 and each is associated with three types of questions: conversational, detailed description, and complex reasoning. We utilize GPT-4 to judge the model outputs.
|
42 |
+
We also evaluate our model on the ScienceQA dataset. Our synergy with GPT-4 sets a new state-of-the-art on the dataset.
|
43 |
+
See https://llava-vl.github.io/ for more details.
|