From c10fdf1d8d5c2f4977cca78853535b66a8e9fc0f Mon Sep 17 00:00:00 2001
From: gongjy <2474590974@qq.com>
Date: Sat, 2 Nov 2024 21:29:01 +0800
Subject: [PATCH] fix bug by xinyanghuang7

---
 model/model.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/model/model.py b/model/model.py
index 79fd7d2..3db3ce0 100644
--- a/model/model.py
+++ b/model/model.py
@@ -387,7 +387,7 @@ class Transformer(PreTrainedModel):
         # 如果此时有图像编码
         if image_encoders is not None:
             vision_proj = self.vision_proj(image_encoders)
-            vision_proj = vision_proj.unsqueeze(0) if len(vision_proj.shape) == 3 else vision_proj
+            vision_proj = vision_proj.unsqueeze(1) if len(vision_proj.shape) == 3 else vision_proj
             if image_indices is not None:
                 # 创建一个新的张量来存储拼接后的结果
                 new_h = []