deepgeek/MiniCPM-o
2
0
Fork 0
mirror of https://github.com/OpenBMB/MiniCPM-V.git synced 2026-02-05 18:29:18 +08:00
Code Issues Packages Projects Releases Wiki Activity

update readme

Browse Source
This commit is contained in:
yiranyyu
2024-05-23 12:26:59 +08:00
parent 4f381b5bf4
commit f39a036940
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docs/compare_with_phi-3_vision.md
View File

@@ -6,9 +6,9 @@ Comparison results of Phi-3-vision-128K-Instruct and MiniCPM-Llama3-V 2.5, regar
## Hardeware Requirements （硬件需求） ## Hardeware Requirements （硬件需求）
With in4 quantization, MiniCPM-Llama3-V 2.5 delivers smooth inference of 6-8 tokens/s with only 8GB of GPU memory. With in4 quantization, MiniCPM-Llama3-V 2.5 delivers smooth inference of 6-8 tokens/s on edge devices with only 8GB of GPU memory.
通过 in4 量化，MiniCPM-Llama3-V 2.5 仅需 8GB 显存即可提供 6-8 tokens/s 的流畅推理。 通过 in4 量化，MiniCPM-Llama3-V 2.5 仅需 8GB 显存即可提供端侧 6-8 tokens/s 的流畅推理。
| Model（模型） | GPU Memory（显存） | | Model（模型） | GPU Memory（显存） |
|:----------------------|:-------------------:| |:----------------------|:-------------------:|
@@ -23,7 +23,7 @@ With in4 quantization, MiniCPM-Llama3-V 2.5 delivers smooth inference of 6-8 tok
| | Phi-3-vision-128K-Instruct | MiniCPM-Llama3-V 2.5| | | Phi-3-vision-128K-Instruct | MiniCPM-Llama3-V 2.5|
|:-|:----------:|:-------------------:| |:-|:----------:|:-------------------:|
| Size（参数） | **4B** | 8B| | Size（参数） | **4B** | 8B|
| OpenCompass | 53.7 | **58.8** | | OpenCompass 2024/05 | 53.7 | **58.8** |
| OCRBench | 639.0 | **725.0**| | OCRBench | 639.0 | **725.0**|
| RealworldQA | 58.8 | **63.5**| | RealworldQA | 58.8 | **63.5**|
| TextVQA | 72.2 | **76.6** | | TextVQA | 72.2 | **76.6** |