Total runs:
2.1M
Run Growth:
-453.0K
Growth Rate:
-21.87%
Sponsored by
APIMaster
jinaai / jina-colbert-v2
Model's Last Updated: August 20 2026
Introduction of jina-colbert-v2
Model Details of jina-colbert-v2
Trained by Jina AI .
JinaColBERT V2: your multilingual late interaction retriever!
JinaColBERT V2 (
jina-colbert-v2
) is a new model based on the
JinaColBERT V1
that expands on the capabilities and performance of the
jina-colbert-v1-en
model. Like the previous release, it has Jina AI’s 8192 token input context and the
improved efficiency, performance
, and
explainability
of token-level embeddings and late interaction.
This new release adds new functionality and performance improvements:
- Multilingual support for dozens of languages, with strong performance on major global languages.
- Matryoshka embeddings , which allow users to trade between efficiency and precision flexibly.
-
Superior retrieval performance when compared to the English-only
jina-colbert-v1-en.
JinaColBERT V2 offers three different versions for different embeddings dimensions:
jinaai/jina-colbert-v2
: 128 dimension embeddings
jinaai/jina-colbert-v2-96
: 96 dimension embeddings
jinaai/jina-colbert-v2-64
: 64 dimension embeddings
Usage
Installation
jina-colbert-v2
is trained with flash attention and therefore requires
einops
and
flash_attn
to be installed.
To use the model, you could either use the Standford ColBERT library or use the
ragatouille
package that we provide.
pip install -U einops flash_attn
pip install -U ragatouille
pip install -U colbert-ai
RAGatouille
from ragatouille import RAGPretrainedModel
RAG = RAGPretrainedModel.from_pretrained("jinaai/jina-colbert-v2")
docs = [
"ColBERT is a novel ranking model that adapts deep LMs for efficient retrieval.",
"Jina-ColBERT is a ColBERT-style model but based on JinaBERT so it can support both 8k context length, fast and accurate retrieval.",
]
RAG.index(docs, index_name="demo")
query = "What does ColBERT do?"
results = RAG.search(query)
Stanford ColBERT
from colbert.infra import ColBERTConfig
from colbert.modeling.checkpoint import Checkpoint
ckpt = Checkpoint("jinaai/jina-colbert-v2", colbert_config=ColBERTConfig())
docs = [
"ColBERT is a novel ranking model that adapts deep LMs for efficient retrieval.",
"Jina-ColBERT is a ColBERT-style model but based on JinaBERT so it can support both 8k context length, fast and accurate retrieval.",
]
query_vectors = ckpt.queryFromText(docs, bsize=2)
Evaluation Results
Retrieval Benchmarks
BEIR
| NDCG@10 | jina-colbert-v2 | jina-colbert-v1 | ColBERTv2.0 | BM25 |
|---|---|---|---|---|
| avg | 0.531 | 0.502 | 0.496 | 0.440 |
| nfcorpus | 0.346 | 0.338 | 0.337 | 0.325 |
| fiqa | 0.408 | 0.368 | 0.354 | 0.236 |
| trec-covid | 0.834 | 0.750 | 0.726 | 0.656 |
| arguana | 0.366 | 0.494 | 0.465 | 0.315 |
| quora | 0.887 | 0.823 | 0.855 | 0.789 |
| scidocs | 0.186 | 0.169 | 0.154 | 0.158 |
| scifact | 0.678 | 0.701 | 0.689 | 0.665 |
| webis-touche | 0.274 | 0.270 | 0.260 | 0.367 |
| dbpedia-entity | 0.471 | 0.413 | 0.452 | 0.313 |
| fever | 0.805 | 0.795 | 0.785 | 0.753 |
| climate-fever | 0.239 | 0.196 | 0.176 | 0.213 |
| hotpotqa | 0.766 | 0.656 | 0.675 | 0.603 |
| nq | 0.640 | 0.549 | 0.524 | 0.329 |
MS MARCO Passage Retrieval
| MRR@10 | jina-colbert-v2 | jina-colbert-v1 | ColBERTv2.0 | BM25 |
|---|---|---|---|---|
| MSMARCO | 0.396 | 0.390 | 0.397 | 0.187 |
Multilingual Benchmarks
MIRACLE
| NDCG@10 | jina-colbert-v2 | mDPR (zero shot) |
|---|---|---|
| avg | 0.627 | 0.427 |
| ar | 0.753 | 0.499 |
| bn | 0.750 | 0.443 |
| de | 0.504 | 0.490 |
| es | 0.538 | 0.478 |
| en | 0.570 | 0.394 |
| fa | 0.563 | 0.480 |
| fi | 0.740 | 0.472 |
| fr | 0.541 | 0.435 |
| hi | 0.600 | 0.383 |
| id | 0.547 | 0.272 |
| ja | 0.632 | 0.439 |
| ko | 0.671 | 0.419 |
| ru | 0.643 | 0.407 |
| sw | 0.499 | 0.299 |
| te | 0.742 | 0.356 |
| th | 0.772 | 0.358 |
| yo | 0.623 | 0.396 |
| zh | 0.523 | 0.512 |
mMARCO
| MRR@10 | jina-colbert-v2 | BM-25 | ColBERT-XM |
|---|---|---|---|
| avg | 0.313 | 0.141 | 0.254 |
| ar | 0.272 | 0.111 | 0.195 |
| de | 0.331 | 0.136 | 0.270 |
| nl | 0.330 | 0.140 | 0.275 |
| es | 0.341 | 0.158 | 0.285 |
| fr | 0.335 | 0.155 | 0.269 |
| hi | 0.309 | 0.134 | 0.238 |
| id | 0.319 | 0.149 | 0.263 |
| it | 0.337 | 0.153 | 0.265 |
| ja | 0.276 | 0.141 | 0.241 |
| pt | 0.337 | 0.152 | 0.276 |
| ru | 0.298 | 0.124 | 0.251 |
| vi | 0.287 | 0.136 | 0.226 |
| zh | 0.302 | 0.116 | 0.246 |
Matryoshka Representation Benchmarks
BEIR
| NDCG@10 | dim=128 | dim=96 | dim=64 |
|---|---|---|---|
| avg | 0.599 | 0.591 | 0.589 |
| nfcorpus | 0.346 | 0.340 | 0.347 |
| fiqa | 0.408 | 0.404 | 0.404 |
| trec-covid | 0.834 | 0.808 | 0.805 |
| hotpotqa | 0.766 | 0.764 | 0.756 |
| nq | 0.640 | 0.640 | 0.635 |
MSMARCO
| MRR@10 | dim=128 | dim=96 | dim=64 |
|---|---|---|---|
| msmarco | 0.396 | 0.391 | 0.388 |
Other Models
Additionally, we provide the following embedding models, you can also use them for retrieval.
-
jina-embeddings-v2-base-en: 137 million parameters. -
jina-embeddings-v2-base-zh: 161 million parameters Chinese-English bilingual model. -
jina-embeddings-v2-base-de: 161 million parameters German-English bilingual model. -
jina-embeddings-v2-base-es: 161 million parameters Spanish-English bilingual model. -
jina-reranker-v2: multilingual reranker model. -
jina-clip-v1: English multimodal (text-image) embedding model.
Contact
Join our Discord community and chat with other community members about ideas.
Runs of jinaai jina-colbert-v2 on huggingface.co
72.8K
Total runs
0
24-hour runs
8.0K
3-day runs
10.2K
7-day runs
-151.6K
30-day runs
More Information About jina-colbert-v2 huggingface.co Model
Url of jina-colbert-v2
jina-colbert-v2 huggingface.co Url
Provider of jina-colbert-v2 huggingface.co
Other API from jinaai
Updated:April 08 2026
Total runs:
1.1M
Run Growth:
190.1K
Growth Rate:
16.72%
Total runs:
1.0M
Run Growth:
-182.8K
Growth Rate:
-17.89%
Total runs:
880.5K
Run Growth:
81.4K
Growth Rate:
9.43%
Total runs:
857.8K
Run Growth:
-21.6K
Growth Rate:
-2.51%
Total runs:
520.6K
Run Growth:
484.8K
Growth Rate:
93.12%
Total runs:
388.4K
Run Growth:
5.1K
Growth Rate:
1.31%
Total runs:
360.3K
Run Growth:
122.6K
Growth Rate:
33.90%
Total runs:
323.7K
Run Growth:
128.0K
Growth Rate:
39.53%
Total runs:
150.4K
Run Growth:
17.6K
Growth Rate:
11.73%
Total runs:
139.5K
Run Growth:
-264.7K
Growth Rate:
-189.65%
Total runs:
137.8K
Run Growth:
-285.6K
Growth Rate:
-207.29%
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:
99.7K
Run Growth:
91.9K
Growth Rate:
92.18%
Total runs:
97.4K
Run Growth:
50.0K
Growth Rate:
57.50%
Total runs:
77.7K
Run Growth:
-17.7K
Growth Rate:
-22.82%
Total runs:
44.0K
Run Growth:
31.9K
Growth Rate:
71.89%
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:
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:
9.3K
Run Growth:
-44.8K
Growth Rate:
-479.86%
Total runs:
7.8K
Run Growth:
-123
Growth Rate:
-1.58%
Total runs:
7.0K
Run Growth:
1.1K
Growth Rate:
15.02%
Total runs:
4.0K
Run Growth:
-532
Growth Rate:
-13.35%
Total runs:
3.8K
Run Growth:
-220
Growth Rate:
-5.87%
Total runs:
3.4K
Run Growth:
3.3K
Growth Rate:
97.56%
Total runs:
3.1K
Run Growth:
1.6K
Growth Rate:
50.10%
Total runs:
3.0K
Run Growth:
-12
Growth Rate:
-0.40%
Total runs:
2.8K
Run Growth:
1.5K
Growth Rate:
51.80%
Total runs:
2.6K
Run Growth:
542
Growth Rate:
20.89%
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:
-51
Growth Rate:
-3.20%
Total runs:
1.5K
Run Growth:
341
Growth Rate:
22.03%
Total runs:
1.5K
Run Growth:
-32
Growth Rate:
-2.13%
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:
1.3K
Run Growth:
-1.1K
Growth Rate:
-91.28%
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:
937
Run Growth:
748
Growth Rate:
79.83%
Total runs:
859
Run Growth:
277
Growth Rate:
32.25%
Total runs:
778
Run Growth:
700
Growth Rate:
89.97%
Total runs:
738
Run Growth:
375
Growth Rate:
50.81%
Total runs:
721
Run Growth:
252
Growth Rate:
34.95%
Total runs:
689
Run Growth:
538
Growth Rate:
78.08%
Total runs:
621
Run Growth:
24
Growth Rate:
3.86%
Total runs:
574
Run Growth:
-98
Growth Rate:
-17.07%
Total runs:
562
Run Growth:
281
Growth Rate:
50.00%
Total runs:
551
Run Growth:
-5
Growth Rate:
-0.91%
Total runs:
514
Run Growth:
182
Growth Rate:
35.41%
Total runs:
502
Run Growth:
231
Growth Rate:
46.02%
Total runs:
379
Run Growth:
110
Growth Rate:
29.02%
Total runs:
338
Run Growth:
-26
Growth Rate:
-7.69%
Total runs:
315
Run Growth:
153
Growth Rate:
48.57%
Total runs:
288
Run Growth:
-166
Growth Rate:
-58.45%
Total runs:
246
Run Growth:
246
Growth Rate:
100.00%
Total runs:
208
Run Growth:
88
Growth Rate:
42.31%
Total runs:
204
Run Growth:
-5
Growth Rate:
-2.45%
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:
156
Run Growth:
104
Growth Rate:
66.67%
Total runs:
148
Run Growth:
-97
Growth Rate:
-65.54%
Total runs:
107
Run Growth:
2
Growth Rate:
1.89%
Total runs:
102
Run Growth:
-22
Growth Rate:
-21.57%
Total runs:
92
Run Growth:
73
Growth Rate:
79.35%
Total runs:
68
Run Growth:
30
Growth Rate:
44.12%
Total runs:
54
Run Growth:
29
Growth Rate:
53.70%
Total runs:
54
Run Growth:
13
Growth Rate:
24.07%
Total runs:
52
Run Growth:
28
Growth Rate:
53.85%
Total runs:
45
Run Growth:
22
Growth Rate:
48.89%
Total runs:
27
Run Growth:
9
Growth Rate:
33.33%
Total runs:
27
Run Growth:
2
Growth Rate:
7.41%