Total runs:
1.8M
Run Growth:
-59.1K
Growth Rate:
-3.18%
Sponsored by
ThumbnailCreator.com
jinaai / jina-embeddings-v4-vllm-code
Model's Last Updated: August 19 2025
visual-document-retrieval
Introduction of jina-embeddings-v4-vllm-code
Model Details of jina-embeddings-v4-vllm-code
The embedding model trained by Jina AI .
Jina Embeddings v4: Universal Embeddings for Multimodal Multilingual Retrieval
Original Model | Blog | Technical Report | API
Model Overview
This repository hosts a vLLM-compatible version of
jina-embeddings-v4
with the
code
adapter merged into the base
Qwen2.5-VL
weights. This architecture modification enables native compatibility with vLLM without requiring custom adapter-handling code.
Usage
import torch
from PIL import Image
from vllm import LLM
from vllm.config import PoolerConfig
from vllm.inputs.data import TextPrompt
# Initialize model
model = LLM(
model="jinaai/jina-embeddings-v4-vllm-code",
task="embed",
override_pooler_config=PoolerConfig(pooling_type="ALL", normalize=False),
dtype="float16",
)
# Create text prompts
query =query = "Find a function that prints a greeting message to the console"
query_prompt = TextPrompt(
prompt=f"Query: {query}"
)
passage = "def hello_world():\n print('Hello, World!')"
passage_prompt = TextPrompt(
prompt=f"Passage: {passage}"
)
# Create image prompt
image = Image.open("<path_to_image>")
image_prompt = TextPrompt(
prompt="<|im_start|>user\n<|vision_start|><|image_pad|><|vision_end|>Describe the image.<|im_end|>\n",
multi_modal_data={"image": image},
)
# Encode all prompts
prompts = [query_prompt, passage_prompt, image_prompt]
outputs = model.encode(prompts)
def get_embeddings(outputs):
VISION_START_TOKEN_ID, VISION_END_TOKEN_ID = 151652, 151653
embeddings = []
for output in outputs:
if VISION_START_TOKEN_ID in output.prompt_token_ids:
# Gather only vision tokens
img_start_pos = torch.where(
torch.tensor(output.prompt_token_ids) == VISION_START_TOKEN_ID
)[0][0]
img_end_pos = torch.where(
torch.tensor(output.prompt_token_ids) == VISION_END_TOKEN_ID
)[0][0]
embeddings_tensor = output.outputs.data.detach().clone()[
img_start_pos : img_end_pos + 1
]
else:
# Use all tokens for text-only prompts
embeddings_tensor = output.outputs.data.detach().clone()
# Pool and normalize embeddings
pooled_output = (
embeddings_tensor.sum(dim=0, dtype=torch.float32)
/ embeddings_tensor.shape[0]
)
embeddings.append(torch.nn.functional.normalize(pooled_output, dim=-1))
return embeddings
embeddings = get_embeddings(outputs)
Runs of jinaai jina-embeddings-v4-vllm-code on huggingface.co
54
Total runs
0
24-hour runs
5
3-day runs
6
7-day runs
29
30-day runs
More Information About jina-embeddings-v4-vllm-code huggingface.co Model
Url of jina-embeddings-v4-vllm-code
jina-embeddings-v4-vllm-code huggingface.co Url
Provider of jina-embeddings-v4-vllm-code huggingface.co
Other API from jinaai
Updated:April 08 2026
Total runs:
1.1M
Run Growth:
190.1K
Growth Rate:
16.72%
Total runs:
1.1M
Run Growth:
53.8K
Growth Rate:
5.49%
Total runs:
1.0M
Run Growth:
-51.5K
Growth Rate:
-5.12%
Total runs:
932.0K
Run Growth:
852.0K
Growth Rate:
91.42%
Total runs:
774.3K
Run Growth:
-107.4K
Growth Rate:
-13.88%
Total runs:
388.4K
Run Growth:
5.1K
Growth Rate:
1.31%
Total runs:
358.4K
Run Growth:
-6.2K
Growth Rate:
-1.74%
Total runs:
166.0K
Run Growth:
-192.2K
Growth Rate:
-115.81%
Total runs:
162.3K
Run Growth:
-148.5K
Growth Rate:
-94.55%
Total runs:
150.7K
Run Growth:
26.6K
Growth Rate:
17.68%
Total runs:
146.1K
Run Growth:
-134.6K
Growth Rate:
-92.09%
Total runs:
106.3K
Run Growth:
37.5K
Growth Rate:
35.31%
Total runs:
105.3K
Run Growth:
-24.5K
Growth Rate:
-23.23%
Total runs:
104.3K
Run Growth:
93.0K
Growth Rate:
89.17%
Total runs:
104.2K
Run Growth:
55.1K
Growth Rate:
51.63%
Total runs:
82.1K
Run Growth:
-34.7K
Growth Rate:
-42.30%
Total runs:
72.8K
Run Growth:
-151.6K
Growth Rate:
-208.22%
Total runs:
57.4K
Run Growth:
-22.2K
Growth Rate:
-38.69%
Total runs:
32.7K
Run Growth:
-1.3K
Growth Rate:
-3.84%
Total runs:
21.0K
Run Growth:
4.7K
Growth Rate:
22.24%
Total runs:
16.9K
Run Growth:
-2.6K
Growth Rate:
-15.32%
Total runs:
15.6K
Run Growth:
-3.0K
Growth Rate:
-19.22%
Total runs:
14.9K
Run Growth:
-27.9K
Growth Rate:
-188.85%
Total runs:
12.2K
Run Growth:
-147
Growth Rate:
-1.20%
Total runs:
12.0K
Run Growth:
-8.7K
Growth Rate:
-72.50%
Total runs:
11.4K
Run Growth:
-14
Growth Rate:
-0.12%
Total runs:
11.0K
Run Growth:
-3.9K
Growth Rate:
-35.57%
Total runs:
9.0K
Run Growth:
7.2K
Growth Rate:
80.10%
Total runs:
8.6K
Run Growth:
-95.4K
Growth Rate:
-1107.65%
Total runs:
7.0K
Run Growth:
1.1K
Growth Rate:
15.02%
Total runs:
6.9K
Run Growth:
-1.1K
Growth Rate:
-15.55%
Total runs:
6.7K
Run Growth:
2.2K
Growth Rate:
32.37%
Total runs:
5.1K
Run Growth:
-195
Growth Rate:
-3.81%
Total runs:
4.0K
Run Growth:
-532
Growth Rate:
-13.35%
Total runs:
4.0K
Run Growth:
-4
Growth Rate:
-0.10%
Total runs:
3.4K
Run Growth:
3.3K
Growth Rate:
97.56%
Total runs:
3.1K
Run Growth:
702
Growth Rate:
22.80%
Total runs:
2.2K
Run Growth:
-88
Growth Rate:
-4.00%
Total runs:
2.2K
Run Growth:
1.1K
Growth Rate:
52.22%
Total runs:
2.1K
Run Growth:
957
Growth Rate:
45.79%
Total runs:
1.9K
Run Growth:
790
Growth Rate:
40.98%
Total runs:
1.8K
Run Growth:
579
Growth Rate:
32.55%
Total runs:
1.7K
Run Growth:
645
Growth Rate:
38.08%
Total runs:
1.7K
Run Growth:
19
Growth Rate:
1.12%
Total runs:
1.6K
Run Growth:
166
Growth Rate:
10.28%
Total runs:
1.6K
Run Growth:
-51
Growth Rate:
-3.20%
Total runs:
1.5K
Run Growth:
341
Growth Rate:
22.03%
Total runs:
1.4K
Run Growth:
588
Growth Rate:
40.98%
Total runs:
1.4K
Run Growth:
-2.4K
Growth Rate:
-172.42%
Total runs:
1.4K
Run Growth:
149
Growth Rate:
10.73%
Total runs:
1.4K
Run Growth:
1.3K
Growth Rate:
95.04%
Total runs:
1.2K
Run Growth:
1.1K
Growth Rate:
89.96%
Total runs:
1.1K
Run Growth:
-91
Growth Rate:
-8.53%
Total runs:
1.0K
Run Growth:
433
Growth Rate:
42.45%
Total runs:
901
Run Growth:
472
Growth Rate:
52.39%
Total runs:
859
Run Growth:
277
Growth Rate:
32.25%
Total runs:
827
Run Growth:
605
Growth Rate:
73.16%
Total runs:
778
Run Growth:
700
Growth Rate:
89.97%
Total runs:
721
Run Growth:
252
Growth Rate:
34.95%
Total runs:
574
Run Growth:
-98
Growth Rate:
-17.07%
Total runs:
567
Run Growth:
49
Growth Rate:
8.78%
Total runs:
551
Run Growth:
-5
Growth Rate:
-0.91%
Total runs:
468
Run Growth:
77
Growth Rate:
16.45%
Total runs:
416
Run Growth:
18
Growth Rate:
4.33%
Total runs:
379
Run Growth:
110
Growth Rate:
29.02%
Total runs:
338
Run Growth:
-26
Growth Rate:
-7.69%
Total runs:
329
Run Growth:
1
Growth Rate:
0.32%
Total runs:
315
Run Growth:
-95
Growth Rate:
-30.16%
Total runs:
315
Run Growth:
153
Growth Rate:
48.57%
Total runs:
246
Run Growth:
246
Growth Rate:
100.00%
Total runs:
208
Run Growth:
88
Growth Rate:
42.31%
Total runs:
194
Run Growth:
57
Growth Rate:
29.38%
Total runs:
186
Run Growth:
39
Growth Rate:
20.97%
Total runs:
183
Run Growth:
10
Growth Rate:
5.46%
Total runs:
180
Run Growth:
91
Growth Rate:
50.56%
Total runs:
159
Run Growth:
0
Growth Rate:
0.00%
Total runs:
149
Run Growth:
-42
Growth Rate:
-28.00%
Total runs:
141
Run Growth:
-56
Growth Rate:
-39.72%
Total runs:
125
Run Growth:
36
Growth Rate:
28.80%
Total runs:
121
Run Growth:
-5
Growth Rate:
-4.13%
Total runs:
102
Run Growth:
-22
Growth Rate:
-21.57%
Total runs:
95
Run Growth:
63
Growth Rate:
66.32%
Total runs:
66
Run Growth:
16
Growth Rate:
24.24%
Total runs:
52
Run Growth:
28
Growth Rate:
53.85%
Total runs:
45
Run Growth:
22
Growth Rate:
48.89%
Total runs:
35
Run Growth:
14
Growth Rate:
40.00%
Total runs:
34
Run Growth:
13
Growth Rate:
38.24%
Total runs:
33
Run Growth:
14
Growth Rate:
41.18%
Total runs:
32
Run Growth:
-18
Growth Rate:
-56.25%