From 71b68adc005665c5b80f67cf9dc66f2fa89ae667 Mon Sep 17 00:00:00 2001
From: Cui Junbo <92843231+Cuiunbo@users.noreply.github.com>
Date: Tue, 6 Aug 2024 22:15:39 +0800
Subject: [PATCH 1/2] update table
---
README.md | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/README.md b/README.md
index 97a02d8..646743b 100644
--- a/README.md
+++ b/README.md
@@ -380,7 +380,7 @@ MiniCPM-V 2.6 can be easily used in various ways: (1) [llama.cpp](https://github
-* We evaluate this benchmark using chain-of-thought prompting.
+* We evaluate this benchmark using chain-of-thought prompting. Specifically, for MME, we used this technique only for the Cognition set.
+ Token Density: number of pixels encoded into each visual token at maximum resolution, i.e., # pixels at maximum resolution / # visual tokens.
From b2be18fa9332ef1e4e0448a01175fdf3681f2641 Mon Sep 17 00:00:00 2001
From: YuzaChongyi <490083538@qq.com>
Date: Wed, 7 Aug 2024 09:57:30 +0800
Subject: [PATCH 2/2] Update README.md
---
README.md | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/README.md b/README.md
index 646743b..92a11e9 100644
--- a/README.md
+++ b/README.md
@@ -93,7 +93,7 @@ Join our 💬 WeChat
- 💪 **Strong OCR Capability and Others.**
MiniCPM-V 2.6 can process images with any aspect ratio and up to 1.8 million pixels (e.g., 1344x1344). It achieves **state-of-the-art performance on OCRBench, surpassing proprietary models such as GPT-4o, GPT-4V, and Gemini 1.5 Pro**.
- Based on the the latest [RLAIF-V](https://github.com/RLHF-V/RLAIF-V/) and [VisCPM](https://github.com/OpenBMB/VisCPM) techniques, it features **trustworthy behaviors**, with significantly lower hallucination rates than GPT-4o and GPT-4V on Object HalBench, and supports **multilingual capabilities** on English, Chiense, German, French, Italian, Korean, etc.
+ Based on the the latest [RLAIF-V](https://github.com/RLHF-V/RLAIF-V/) and [VisCPM](https://github.com/OpenBMB/VisCPM) techniques, it features **trustworthy behaviors**, with significantly lower hallucination rates than GPT-4o and GPT-4V on Object HalBench, and supports **multilingual capabilities** on English, Chinese, German, French, Italian, Korean, etc.
- 🚀 **Superior Efficiency.**