Update README.md
Browse files
README.md
CHANGED
@@ -3,11 +3,11 @@ pipeline_tag: text-generation
|
|
3 |
---
|
4 |
|
5 |
## MiniCPM-V
|
6 |
-
**MiniCPM-V** (i.e., OmniLMM-3B)is an efficient version with promising performance for deployment. The model is built based on [MiniCPM-
|
7 |
|
8 |
-
-
|
9 |
|
10 |
-
MiniCPM-V can be **efficiently deployed on most GPU cards and personal computers**, and **even on
|
11 |
|
12 |
- π₯ **Promising Performance.**
|
13 |
|
@@ -15,7 +15,7 @@ pipeline_tag: text-generation
|
|
15 |
|
16 |
- π **Bilingual Support.**
|
17 |
|
18 |
-
MiniCPM-V is **the first
|
19 |
|
20 |
### Evaluation
|
21 |
|
@@ -107,6 +107,9 @@ pipeline_tag: text-generation
|
|
107 |
## Demo
|
108 |
Click here to try out the Demo of [MiniCPM-V](http://120.92.209.146:80).
|
109 |
|
|
|
|
|
|
|
110 |
|
111 |
## Usage
|
112 |
Requirements: tested on python 3.10
|
@@ -146,6 +149,7 @@ print(res)
|
|
146 |
|
147 |
|
148 |
## License
|
|
|
149 |
#### Model License
|
150 |
* The code in this repo is released according to [Apache-2.0](https://github.com/OpenBMB/MiniCPM/blob/main/LICENSE)
|
151 |
* The usage of MiniCPM-V's parameters is subject to ["General Model License Agreement - Source Notes - Publicity Restrictions - Commercial License"](https://github.com/OpenBMB/General-Model-License/blob/main/)
|
|
|
3 |
---
|
4 |
|
5 |
## MiniCPM-V
|
6 |
+
**MiniCPM-V** (i.e., OmniLMM-3B)is an efficient version with promising performance for deployment. The model is built based on SigLip-400M and [MiniCPM-2.4B](https://github.com/OpenBMB/MiniCPM/), connected by a perceiver resampler. Notable features of OmniLMM-3B include:
|
7 |
|
8 |
+
- β‘οΈ **High Efficiency.**
|
9 |
|
10 |
+
MiniCPM-V can be **efficiently deployed on most GPU cards and personal computers**, and **even on end devices such as mobile phones**. In terms of visual encoding, we compress the image representations into 64 tokens via a perceiver resampler, which is significantly fewer than other LMMs based on MLP architecture (typically > 512 tokens). This allows OmniLMM-3B to operate with **much less memory cost and higher speed during inference**.
|
11 |
|
12 |
- π₯ **Promising Performance.**
|
13 |
|
|
|
15 |
|
16 |
- π **Bilingual Support.**
|
17 |
|
18 |
+
MiniCPM-V is **the first end-deployable LMM supporting bilingual multimodal interaction in English and Chinese**. This is achieved by generalizing multimodal capabilities across languages, a technique from the ICLR 2024 spotlight [paper](https://arxiv.org/abs/2308.12038).
|
19 |
|
20 |
### Evaluation
|
21 |
|
|
|
107 |
## Demo
|
108 |
Click here to try out the Demo of [MiniCPM-V](http://120.92.209.146:80).
|
109 |
|
110 |
+
## Deployment on Mobile Phone
|
111 |
+
Currently MiniCPM-V (i.e., OmniLMM-3B) can be deployed on mobile phones with Android and Harmony operating systems. π Try it out [here](https://github.com/OpenBMB/mlc-MiniCPM).
|
112 |
+
|
113 |
|
114 |
## Usage
|
115 |
Requirements: tested on python 3.10
|
|
|
149 |
|
150 |
|
151 |
## License
|
152 |
+
|
153 |
#### Model License
|
154 |
* The code in this repo is released according to [Apache-2.0](https://github.com/OpenBMB/MiniCPM/blob/main/LICENSE)
|
155 |
* The usage of MiniCPM-V's parameters is subject to ["General Model License Agreement - Source Notes - Publicity Restrictions - Commercial License"](https://github.com/OpenBMB/General-Model-License/blob/main/)
|