zRzRzRzRzRzRzR
commited on
fix wrong image
Browse files
README.md
CHANGED
@@ -16,7 +16,7 @@ inference: false
|
|
16 |
# CogVLM2
|
17 |
|
18 |
<div align="center">
|
19 |
-
<img src=https://
|
20 |
</div>
|
21 |
<p align="center">
|
22 |
π Join us on <a href="https://github.com/THUDM/CogVLM2/blob/main/resources/WECHAT.md" target="_blank">WeChat</a>
|
@@ -52,6 +52,7 @@ Our open source models have achieved good results in many lists compared to the
|
|
52 |
|
53 |
| Model | Open Source | LLM Size | TextVQA | DocVQA | ChartQA | OCRbench | MMMU | MMVet | MMBench |
|
54 |
|--------------------------------|-------------|----------|----------|----------|----------|----------|----------|----------|----------|
|
|
|
55 |
| LLaVA-1.5 | β
| 13B | 61.3 | - | - | 337 | 37.0 | 35.4 | 67.7 |
|
56 |
| Mini-Gemini | β
| 34B | 74.1 | - | - | - | 48.0 | 59.3 | 80.6 |
|
57 |
| LLaVA-NeXT-LLaMA3 | β
| 8B | - | 78.2 | 69.5 | - | 41.7 | - | 72.1 |
|
@@ -61,7 +62,7 @@ Our open source models have achieved good results in many lists compared to the
|
|
61 |
| Claude3-Opus | β | - | - | 89.3 | 80.8 | 694 | **59.4** | 51.7 | 63.3 |
|
62 |
| Gemini Pro 1.5 | β | - | 73.5 | 86.5 | 81.3 | - | 58.5 | - | - |
|
63 |
| GPT-4V | β | - | 78.0 | 88.4 | 78.5 | 656 | 56.8 | **67.7** | 75.0 |
|
64 |
-
| CogVLM1.1
|
65 |
| CogVLM2-LLaMA3 (Ours) | β
| 8B | 84.2 | **92.3** | 81.0 | 756 | 44.3 | 60.4 | 80.5 |
|
66 |
| CogVLM2-LLaMA3-Chinese (Ours) | β
| 8B | **85.0** | 88.4 | 74.7 | **780** | 42.8 | 60.5 | 78.9 |
|
67 |
|
|
|
16 |
# CogVLM2
|
17 |
|
18 |
<div align="center">
|
19 |
+
<img src=https://raw.githubusercontent.com/THUDM/CogVLM2/53d5d5ea1aa8d535edffc0d15e31685bac40f878/resources/logo.svg width="40%"/>
|
20 |
</div>
|
21 |
<p align="center">
|
22 |
π Join us on <a href="https://github.com/THUDM/CogVLM2/blob/main/resources/WECHAT.md" target="_blank">WeChat</a>
|
|
|
52 |
|
53 |
| Model | Open Source | LLM Size | TextVQA | DocVQA | ChartQA | OCRbench | MMMU | MMVet | MMBench |
|
54 |
|--------------------------------|-------------|----------|----------|----------|----------|----------|----------|----------|----------|
|
55 |
+
| CogVLM1.1 | β
| 7B | 69.7 | - | 68.3 | 590 | 37.3 | 52.0 | 65.8 |
|
56 |
| LLaVA-1.5 | β
| 13B | 61.3 | - | - | 337 | 37.0 | 35.4 | 67.7 |
|
57 |
| Mini-Gemini | β
| 34B | 74.1 | - | - | - | 48.0 | 59.3 | 80.6 |
|
58 |
| LLaVA-NeXT-LLaMA3 | β
| 8B | - | 78.2 | 69.5 | - | 41.7 | - | 72.1 |
|
|
|
62 |
| Claude3-Opus | β | - | - | 89.3 | 80.8 | 694 | **59.4** | 51.7 | 63.3 |
|
63 |
| Gemini Pro 1.5 | β | - | 73.5 | 86.5 | 81.3 | - | 58.5 | - | - |
|
64 |
| GPT-4V | β | - | 78.0 | 88.4 | 78.5 | 656 | 56.8 | **67.7** | 75.0 |
|
65 |
+
| CogVLM1.1 | β
| 7B | 69.7 | - | 68.3 | 590 | 37.3 | 52.0 | 65.8 |
|
66 |
| CogVLM2-LLaMA3 (Ours) | β
| 8B | 84.2 | **92.3** | 81.0 | 756 | 44.3 | 60.4 | 80.5 |
|
67 |
| CogVLM2-LLaMA3-Chinese (Ours) | β
| 8B | **85.0** | 88.4 | 74.7 | **780** | 42.8 | 60.5 | 78.9 |
|
68 |
|