Hugging Face's logo

MILVLG
/
Imp-v1.5-3B-Phi2

Text Generation
Transformers
Safetensors
imp
custom_code
Model card Files Community
Oyoy1235 commited on
Commit
04b5feb
•
1 Parent(s): 93e3896

update readme

Browse files
Files changed (1) hide show
  1. README.md +5 -11
README.md CHANGED
@@ -6,12 +6,6 @@ datasets:
6
  - liuhaotian/LLaVA-Instruct-150K
7
  ---
8
  # 😈 Imp
9
-
10
- > A very small man can cast a very large shadow.
11
- >
12
- >           ——*George R.R. Martin, A Clash of Kings*
13
-
14
-
15
  \[[Paper](https://arxiv.org/abs/2405.12107)\]  [[Demo](https://xmbot.net/imp/)\]  [[Github](https://github.com/MILVLG/imp)\]
16
 
17
  ## Introduction
@@ -70,13 +64,13 @@ We conduct evaluation on 9 commonly-used benchmarks, including 5 academic VQA be
70
 
71
  | Models | Size | VQAv2 | GQA | SQA(IMG) | TextVQA | POPE | MME(P) | MMB |MMBCN |MM-Vet|
72
  |:--------:|:-----:|:----:|:-------------:|:--------:|:-----:|:----:|:-------:|:-------:|:-------:|:-------:|
73
- | [LLaVA-v1.5-lora](https://huggingface.co/liuhaotian/llava-v1.5-7b) | 7B |79.10 | 63.00| 68.40 |58.20| 86.40 | 1476.9 | 66.10 |- |30.2|
74
  | [TinyGPT-V-3B](https://huggingface.co/Tyrannosaurus/TinyGPT-V) | 3B | - | 38.9 | - | - | -| - | - |- |-|
75
- | [LaVA-Phi-3B](https://github.com/zhuyiche/llava-phi) | 3B | 71.40 | - | 68.40 | 48.60 | 85.00 | 1335.1 | 59.80 |-|28.9|
76
- | [MobileVLM-3B](https://huggingface.co/mtgv/MobileVLM-3B) | 3B | - | 59.00 | 61.00 | 47.50 | 84.90 | 1288.9 | 59.60 |- |-|
77
- | [MiniCPM-V-3B](https://huggingface.co/mtgv/MobileVLM-3B) | 3B | - |- | - | - | - | 1452.0 | 67.9 | 65.3 |-|
78
  | [Bunny-3B](https://huggingface.co/visheratin/MC-LLaVA-3b) | 3B | 79.8 | 62.5 | 70.9 | - | 86.8| 1488.8 | 68.6 |- |-|
79
- | **Imp-v1.5-3B-Phi2** | 3B | **81.18** | **63.54** | **72.78**| **59.84** | **88.87**| **1446.4** | **72.94**| 46.65 |**43.3**|
80
 
81
  ## License
82
  This project is licensed under the Apache License 2.0 - see the [LICENSE](https://www.apache.org/licenses/LICENSE-2.0) file for details.
 
6
  - liuhaotian/LLaVA-Instruct-150K
7
  ---
8
  # 😈 Imp
 
 
 
 
 
 
9
  \[[Paper](https://arxiv.org/abs/2405.12107)\]  [[Demo](https://xmbot.net/imp/)\]  [[Github](https://github.com/MILVLG/imp)\]
10
 
11
  ## Introduction
 
64
 
65
  | Models | Size | VQAv2 | GQA | SQA(IMG) | TextVQA | POPE | MME(P) | MMB |MMBCN |MM-Vet|
66
  |:--------:|:-----:|:----:|:-------------:|:--------:|:-----:|:----:|:-------:|:-------:|:-------:|:-------:|
67
+ | [LLaVA-v1.5-lora](https://huggingface.co/liuhaotian/llava-v1.5-7b) | 7B |79.1 | 63.0| 68.4 |58.2| 86.4 | 1476.9 | 66.1 |- |30.2|
68
  | [TinyGPT-V-3B](https://huggingface.co/Tyrannosaurus/TinyGPT-V) | 3B | - | 38.9 | - | - | -| - | - |- |-|
69
+ | [LaVA-Phi-3B](https://github.com/zhuyiche/llava-phi) | 3B | 71.4 | - | 68.4 | 48.6 | 85.0 | 1335.1 | 59.8 |-|28.9|
70
+ | [MobileVLM-3B](https://huggingface.co/mtgv/MobileVLM-3B) | 3B | - | 59.0 | 61.0 | 47.5 | 84.9 | 1288.9 | 59.6 |- |-|
71
+ | [MiniCPM-V-3B](https://huggingface.co/mtgv/MobileVLM-3B) | 3B | - |- | - | - | - | 1452.0 | 67.9 | **65.3**|-|
72
  | [Bunny-3B](https://huggingface.co/visheratin/MC-LLaVA-3b) | 3B | 79.8 | 62.5 | 70.9 | - | 86.8| 1488.8 | 68.6 |- |-|
73
+ | **Imp-v1.5-3B-Phi2** | 3B | **81.2** | **63.5** | **72.8**| **59.8** | **88.9**| **1446.4** | **72.9**| 46.7 |**43.3**|
74
 
75
  ## License
76
  This project is licensed under the Apache License 2.0 - see the [LICENSE](https://www.apache.org/licenses/LICENSE-2.0) file for details.