biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Bugfix] Fix ModernBert load & Enable sliding window attention for bidirectional attention. (#22637)

Browse Source 
Signed-off-by: wang.yuqi <noooop@126.com>
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Max de Bayser <mbayser@br.ibm.com>
This commit is contained in:
wang.yuqi
2025-08-12 15:23:17 +08:00
committed by GitHub
parent 2f4657952b
commit 6d729c43fb
4 changed files with 101 additions and 59 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
tests/models/language/pooling/test_gte.py
View File

@@ -4,10 +4,11 @@ from typing import Any
import pytest
from ...utils import (CLSPoolingEmbedModelInfo, EmbedModelInfo,
LASTPoolingEmbedModelInfo, check_transformers_version)
from ...utils import (CLSPoolingEmbedModelInfo, CLSPoolingRerankModelInfo,
EmbedModelInfo, LASTPoolingEmbedModelInfo,
RerankModelInfo, check_transformers_version)
from .embed_utils import correctness_test_embed_models
from .mteb_utils import mteb_test_embed_models
from .mteb_utils import mteb_test_embed_models, mteb_test_rerank_models
MODELS = [
########## BertModel
@@ -58,6 +59,14 @@ MODELS = [
enable_test=False),
]
RERANK_MODELS = [
# classifier_pooling: mean
CLSPoolingRerankModelInfo(
"Alibaba-NLP/gte-reranker-modernbert-base",
architecture="ModernBertForSequenceClassification",
enable_test=True),
]
@pytest.mark.parametrize("model_info", MODELS)
def test_embed_models_mteb(hf_runner, vllm_runner,
@@ -88,3 +97,9 @@ def test_embed_models_correctness(hf_runner, vllm_runner,
correctness_test_embed_models(hf_runner, vllm_runner, model_info,
example_prompts, vllm_extra_kwargs)
@pytest.mark.parametrize("model_info", RERANK_MODELS)
def test_rerank_models_mteb(hf_runner, vllm_runner,
model_info: RerankModelInfo) -> None:
mteb_test_rerank_models(hf_runner, vllm_runner, model_info)