From 859823eb23776b610ae632d10e889b8242581aa5 Mon Sep 17 00:00:00 2001
From: hiyouga <467089858@qq.com>
Date: Mon, 2 Sep 2024 01:31:36 +0800
Subject: [PATCH] add image num check

Former-commit-id: ce8c5a264742161101da2094d0fc31c7fa7fb641
---
 src/llamafactory/data/mm_plugin.py | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/src/llamafactory/data/mm_plugin.py b/src/llamafactory/data/mm_plugin.py
index a3636737..47682732 100644
--- a/src/llamafactory/data/mm_plugin.py
+++ b/src/llamafactory/data/mm_plugin.py
@@ -210,12 +210,17 @@ class Qwen2vlPlugin(BasePlugin):
         merge_length: int = getattr(image_processor, "merge_size") ** 2
         if len(images) > 0:
             image_grid_thw = _get_mm_inputs(images, processor)["image_grid_thw"]
+        else:
+            image_grid_thw = []
 
         num_images = 0
         messages = deepcopy(messages)
         for message in messages:
             content = message["content"]
             while IMAGE_PLACEHOLDER in content:
+                if num_images >= len(image_grid_thw):
+                    raise ValueError("`len(images)` is less than the number of {} tokens.".format(IMAGE_PLACEHOLDER))
+
                 content = content.replace(
                     IMAGE_PLACEHOLDER,
                     "<|vision_start|>{}<|vision_end|>".format(