Add support for Qwen2-VL-based embedding models (#2055)

2024-11-21 17:24:25 -05:00
parent f35cb46cc3
commit f6f713797b
4 changed files with 39 additions and 12 deletions
--- a/test/srt/models/test_embedding_models.py
+++ b/test/srt/models/test_embedding_models.py
@@ -25,6 +25,7 @@ from sglang.test.test_utils import get_similarities
 MODELS = [
    ("Alibaba-NLP/gte-Qwen2-1.5B-instruct", 1, 1e-5),
    ("intfloat/e5-mistral-7b-instruct", 1, 1e-5),
+    ("marco/mcdse-2b-v1", 1, 1e-5),
 ]
 TORCH_DTYPES = [torch.float16]