chenlin
commited on
Commit
•
0d4ba7a
1
Parent(s):
bd022dc
update readme
Browse files
README.md
CHANGED
@@ -1,3 +1,35 @@
|
|
1 |
---
|
2 |
-
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
inference: false
|
3 |
---
|
4 |
+
<br>
|
5 |
+
<br>
|
6 |
+
|
7 |
+
# ShareGPT4V-7B Model Card
|
8 |
+
|
9 |
+
## Model details
|
10 |
+
|
11 |
+
**Model type:**
|
12 |
+
This is the pre-trained LLM and projector of ShareGPT4v-7B
|
13 |
+
|
14 |
+
**Model date:**
|
15 |
+
ShareGPT4V-7B-Pretrained was trained in Nov 2023.
|
16 |
+
|
17 |
+
**Paper or resources for more information:**
|
18 |
+
[[Project](https://ShareGPT4V.github.io/)] [[Paper](https://huggingface.co/papers/2311.12793)] [[Code](https://github.com/InternLM/InternLM-XComposer/tree/main/projects/ShareGPT4V)] [[Dataset](https://huggingface.co/datasets/Lin-Chen/ShareGPT4V)]
|
19 |
+
|
20 |
+
## Usage
|
21 |
+
You can directly utilize this model as we provide in our [[repository](https://github.com/InternLM/InternLM-XComposer/tree/main/projects/ShareGPT4V)]. Moreover, you can modify the architecture name from "Share4VLlamaForCausalLM" to "LLaVALlamaForCausalLM" and the model_type keyword from "share4v" to "llava" in our config file and seamlessly load our model in the [[LLaVA repository](https://github.com/haotian-liu/LLaVA)].
|
22 |
+
|
23 |
+
## License
|
24 |
+
Llama 2 is licensed under the LLAMA 2 Community License,
|
25 |
+
Copyright (c) Meta Platforms, Inc. All Rights Reserved.
|
26 |
+
|
27 |
+
## Intended use
|
28 |
+
**Primary intended uses:**
|
29 |
+
The primary use of ShareGPT4V-7B is research on large multimodal models and chatbots.
|
30 |
+
|
31 |
+
**Primary intended users:**
|
32 |
+
The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.
|
33 |
+
|
34 |
+
## Training dataset
|
35 |
+
- 1.2M high-quality image-text pairs, i.e., ShareGPT4V-PT data
|