From 814241a4cd4aeef0e2a032b6cb758a9bd9d00abb Mon Sep 17 00:00:00 2001
From: GeLee <865038696@qq.com>
Date: Fri, 6 Sep 2024 20:19:29 +0800
Subject: [PATCH] add self.head_dim for VisionAttention in Qwen2-VL (#33211)

* add self.head_dim for VisionAttention in Qwen2-VL

* add self.head_dim for VisionAttention in Qwen2-VL

* fix ci

* black the test_modeling_qwen2_vl.py

* use ruff to format test_modeling_qwen2_vl.py

* [run-slow] qwen2_vl

* use tying for python3.8

* fix the import format

* use ruff to fix the ci error I001

* [run-slow] qwen2_vl

* remove unused import

* commit for rebase

* use ruff fix ci

* [run-slow] qwen2_vl

---------

Co-authored-by: root <liji>
---
 tests/models/qwen2_vl/test_modeling_qwen2_vl.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tests/models/qwen2_vl/test_modeling_qwen2_vl.py b/tests/models/qwen2_vl/test_modeling_qwen2_vl.py
index 536e0ab54abc45..4bd85f06a4f952 100644
--- a/tests/models/qwen2_vl/test_modeling_qwen2_vl.py
+++ b/tests/models/qwen2_vl/test_modeling_qwen2_vl.py
@@ -164,7 +164,9 @@ def prepare_config_and_inputs_for_common(self):
         attention_mask = torch.ones(input_ids.shape, dtype=torch.long, device=torch_device)
         input_ids[:, torch.arange(vision_seqlen, device=torch_device) + 1] = self.image_token_id
         labels = torch.zeros(
-            (self.batch_size, self.seq_length - 1 + vision_seqlen), dtype=torch.long, device=torch_device
+            (self.batch_size, self.seq_length - 1 + vision_seqlen),
+            dtype=torch.long,
+            device=torch_device,
         )
         patch_size = self.vision_config["patch_size"]
         inputs_dict = {