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

[CI/Build][Doc] Update gte-Qwen2-1.5B-instruct usage (#18683)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
This commit is contained in:
Cyrus Leung
2025-05-26 11:27:50 +08:00
committed by GitHub
parent 6071e989df
commit fba0642704
3 changed files with 2 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
tests/models/language/pooling/test_gte.py
View File

@@ -45,9 +45,6 @@ MODELS = [
EmbedModelInfo("Alibaba-NLP/gte-Qwen2-1.5B-instruct",
architecture="Qwen2ForCausalLM",
enable_test=True),
EmbedModelInfo("Alibaba-NLP/gte-Qwen2-7B-instruct",
architecture="Qwen2ForCausalLM",
enable_test=False),
########## ModernBertModel
EmbedModelInfo("Alibaba-NLP/gte-modernbert-base",
architecture="ModernBertModel",
@@ -61,9 +58,6 @@ def test_models_mteb(hf_runner, vllm_runner,
from .mteb_utils import mteb_test_embed_models
vllm_extra_kwargs: dict[str, Any] = {}
if model_info.name == "Alibaba-NLP/gte-Qwen2-1.5B-instruct":
vllm_extra_kwargs["hf_overrides"] = {"is_causal": True}
if model_info.architecture == "GteNewModel":
vllm_extra_kwargs["hf_overrides"] = {"architectures": ["GteNewModel"]}
@@ -81,9 +75,6 @@ def test_models_correctness(hf_runner, vllm_runner, model_info: EmbedModelInfo,
example_prompts = [str(s).strip() for s in example_prompts]
vllm_extra_kwargs: dict[str, Any] = {}
if model_info.name == "Alibaba-NLP/gte-Qwen2-1.5B-instruct":
vllm_extra_kwargs["hf_overrides"] = {"is_causal": True}
if model_info.architecture == "GteNewModel":
vllm_extra_kwargs["hf_overrides"] = {"architectures": ["GteNewModel"]}