update
Browse files
README.md
CHANGED
|
@@ -2,10 +2,11 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
-
pipeline_tag: Multimodal Small Language Model,
|
| 6 |
---
|
| 7 |
# :smiling_imp: IMP
|
| 8 |
|
|
|
|
| 9 |
The :smiling_imp: IMP project aims to provide a family of a strong multimodal `small` language models (MSLMs). Our `IMP-v0-3B` model is a strong MSLM with only **3B** parameters, which is build upon a small yet powerful SLM [Phi-2 ](https://huggingface.co/microsoft/phi-2)(2.7B) and a powerful visual encoder [SigLIP ](https://huggingface.co/google/siglip-so400m-patch14-384)(0.4B), and trained on the [LLaVA-v1.5](https://github.com/haotian-liu/LLaVA) training set.
|
| 10 |
|
| 11 |
As shown in the Table below, `IMP-v0-3B` significantly outperforms the counterparts of similar model sizes, and even achieves slightly better performance than the strong LLaVA-7B model on various multimodal benchmarks.
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
+
pipeline_tag: Multimodal Small Language Model, visual-question-answering
|
| 6 |
---
|
| 7 |
# :smiling_imp: IMP
|
| 8 |
|
| 9 |
+
|
| 10 |
The :smiling_imp: IMP project aims to provide a family of a strong multimodal `small` language models (MSLMs). Our `IMP-v0-3B` model is a strong MSLM with only **3B** parameters, which is build upon a small yet powerful SLM [Phi-2 ](https://huggingface.co/microsoft/phi-2)(2.7B) and a powerful visual encoder [SigLIP ](https://huggingface.co/google/siglip-so400m-patch14-384)(0.4B), and trained on the [LLaVA-v1.5](https://github.com/haotian-liu/LLaVA) training set.
|
| 11 |
|
| 12 |
As shown in the Table below, `IMP-v0-3B` significantly outperforms the counterparts of similar model sizes, and even achieves slightly better performance than the strong LLaVA-7B model on various multimodal benchmarks.
|