Add license, paper link, GitHub, and project page to model card
Browse filesThis PR enhances the model card for `openbmb/MiniCPM-o-2_6-int4` by:
- Adding the `license: apache-2.0` to the metadata block, as indicated in the official GitHub repository.
- Including a direct link to the associated research paper: [MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe](https://huggingface.co/papers/2509.18154).
- Providing a link to the main GitHub repository: [https://github.com/OpenBMB/MiniCPM-V](https://github.com/OpenBMB/MiniCPM-V).
- Adding a link to the project's online demo/project page: [https://minicpm-omni-webdemo-us.modelbest.cn/](https://minicpm-omni-webdemo-us.modelbest.cn/).
These additions improve the completeness and discoverability of information about the model for users and researchers.
|
@@ -1,10 +1,12 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
| 3 |
datasets:
|
| 4 |
- openbmb/RLAIF-V-Dataset
|
| 5 |
-
library_name: transformers
|
| 6 |
language:
|
| 7 |
- multilingual
|
|
|
|
|
|
|
| 8 |
tags:
|
| 9 |
- minicpm-o
|
| 10 |
- omni
|
|
@@ -20,10 +22,15 @@ tags:
|
|
| 20 |
- realtime speech conversation
|
| 21 |
- asr
|
| 22 |
- tts
|
| 23 |
-
|
| 24 |
-
- openbmb/MiniCPM-o-2_6
|
| 25 |
---
|
| 26 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
<h1>A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone</h1>
|
| 28 |
|
| 29 |
## MiniCPM-o 2.6 int4
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model:
|
| 3 |
+
- openbmb/MiniCPM-o-2_6
|
| 4 |
datasets:
|
| 5 |
- openbmb/RLAIF-V-Dataset
|
|
|
|
| 6 |
language:
|
| 7 |
- multilingual
|
| 8 |
+
library_name: transformers
|
| 9 |
+
pipeline_tag: any-to-any
|
| 10 |
tags:
|
| 11 |
- minicpm-o
|
| 12 |
- omni
|
|
|
|
| 22 |
- realtime speech conversation
|
| 23 |
- asr
|
| 24 |
- tts
|
| 25 |
+
license: apache-2.0
|
|
|
|
| 26 |
---
|
| 27 |
|
| 28 |
+
This model is part of the MiniCPM project. For the latest research and technical details, please refer to the technical report:
|
| 29 |
+
[MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe](https://huggingface.co/papers/2509.18154)
|
| 30 |
+
|
| 31 |
+
Code Repository: [https://github.com/OpenBMB/MiniCPM-V](https://github.com/OpenBMB/MiniCPM-V)
|
| 32 |
+
Project Homepage: [https://minicpm-omni-webdemo-us.modelbest.cn/](https://minicpm-omni-webdemo-us.modelbest.cn/)
|
| 33 |
+
|
| 34 |
<h1>A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone</h1>
|
| 35 |
|
| 36 |
## MiniCPM-o 2.6 int4
|