jinaai
/

jina-embeddings-v4-vllm-retrieval

Visual Document Retrieval

multimodal-embedding

multilingual-embedding

Text-to-Visual Document (T→VD) retrieval

feature-extraction

sentence-similarity

text-generation-inference

🇪🇺 Region: EU

Model card Files Files and versions Community

florian-hoenicke commited on 1 day ago

Commit

1c64a04

·

verified ·

1 Parent(s): b5fe259

docs: work around

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -48,7 +48,7 @@ from vllm.inputs.data import TextPrompt
 # Initialize model
 model = LLM(
     model="jinaai/jina-embeddings-v4-vllm-retrieval",
-    task="embed",
     override_pooler_config=PoolerConfig(pooling_type="ALL", normalize=False),
     dtype="float16",
 )

 # Initialize model
 model = LLM(
     model="jinaai/jina-embeddings-v4-vllm-retrieval",
+    task="auto",
     override_pooler_config=PoolerConfig(pooling_type="ALL", normalize=False),
     dtype="float16",
 )