anonymitaet
commited on
Commit
•
a8fa12e
1
Parent(s):
eaa29e6
update readme
Browse files
README.md
CHANGED
@@ -57,7 +57,8 @@ license_link: LICENSE
|
|
57 |
- [Why Yi-VL?](#why-yi-vl)
|
58 |
- [Benchmarks](#benchmarks)
|
59 |
- [How to use Yi-VL?](#how-to-use-yi-vl)
|
60 |
-
- [Quick
|
|
|
61 |
|
62 |
</details>
|
63 |
|
@@ -172,7 +173,7 @@ Yi-VL outperforms all existing open-source models in [MMMU](https://mmmu-benchma
|
|
172 |
|
173 |
# How to use Yi-VL?
|
174 |
|
175 |
-
## Quick
|
176 |
|
177 |
You can perform inference using the code from [LLaVA](https://github.com/haotian-liu/LLaVA). For detailed steps, see [simple startup for pretraining](https://github.com/haotian-liu/LLaVA/pull/966).
|
178 |
|
@@ -188,4 +189,33 @@ Notes:
|
|
188 |
### Assistant:
|
189 |
```
|
190 |
|
191 |
-
- You need to set the parameter `mm_vision_tower` in `config.json` to the local ViT path.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
57 |
- [Why Yi-VL?](#why-yi-vl)
|
58 |
- [Benchmarks](#benchmarks)
|
59 |
- [How to use Yi-VL?](#how-to-use-yi-vl)
|
60 |
+
- [Quick start](#quick-start)
|
61 |
+
- [Acknowledgements and attributions](#acknowledgements-and-attributions)
|
62 |
|
63 |
</details>
|
64 |
|
|
|
173 |
|
174 |
# How to use Yi-VL?
|
175 |
|
176 |
+
## Quick start
|
177 |
|
178 |
You can perform inference using the code from [LLaVA](https://github.com/haotian-liu/LLaVA). For detailed steps, see [simple startup for pretraining](https://github.com/haotian-liu/LLaVA/pull/966).
|
179 |
|
|
|
189 |
### Assistant:
|
190 |
```
|
191 |
|
192 |
+
- You need to set the parameter `mm_vision_tower` in `config.json` to the local ViT path.
|
193 |
+
|
194 |
+
# Acknowledgements and attributions
|
195 |
+
|
196 |
+
This project makes use of open-source software/components. We acknowledge and are grateful to these developers for their contributions to the open-source community.
|
197 |
+
|
198 |
+
## List of used open-source projects
|
199 |
+
|
200 |
+
1. LLaVA
|
201 |
+
- Authors: Haotian Liu, Chunyuan Li, Qingyang Wu, Yuheng Li, and Yong Jae Lee
|
202 |
+
- Source: https://github.com/haotian-liu/LLaVA
|
203 |
+
- License: Apache-2.0 license
|
204 |
+
- Description: The codebase is based on LLaVA code.
|
205 |
+
|
206 |
+
2. OpenClip
|
207 |
+
- Authors: Gabriel Ilharco, Mitchell Wortsman, Ross Wightman, Cade Gordon, Nicholas Carlini, Rohan Taori, Achal Dave, Vaishaal Shankar, Hongseok Namkoong, John Miller, Hannaneh Hajishirzi, Ali Farhadi, and Ludwig Schmidt
|
208 |
+
- Source: https://huggingface.co/laion/CLIP-ViT-H-14-laion2B-s32B-b79K
|
209 |
+
- License: mit
|
210 |
+
- Description: The ViT is initialized using the weights of OpenClip.
|
211 |
+
|
212 |
+
## License
|
213 |
+
|
214 |
+
This project is licensed under the [yi-license](https://github.com/01-ai/Yi/blob/main/LICENSE). For more information on the license for this project, please see the LICENSE file in this repository.
|
215 |
+
|
216 |
+
## Notes
|
217 |
+
|
218 |
+
- This attribution does not claim to cover all open-source components used. Please check individual components and their respective licenses for full details.
|
219 |
+
- The use of the open-source components is subject to the terms and conditions of the respective licenses.
|
220 |
+
|
221 |
+
We appreciate the open-source community for their invaluable contributions to the technology world.
|