← Catalog
lightonai/GTE-ModernColBERT-v1 Add to compare Open comparison →
Primitive: /score · Score ·
ModernBERT
This is a PyLate model trained on the ms-marco-en-bge-gemma dataset. It maps sentences & paragraphs to sequences of 128-dimensional dense vectors and can be used for semantic textual similarity using the MaxSim operator.
Long context
View on Hugging Face → Fine-tuned from Alibaba-NLP/gte-modernbert-base
Overview
Hardware:
L4 RTX-PRO-6000 — drives latency, throughput & cost
Size 149M params Tasks /encode · /score License apache-2.0 Latency 313 ms Throughput 231 tok/s Cost $0.961 /1M tok
Cost is approximate — computed from list GPU prices; your actual price depends on the provider you deploy SIE with.
Scoring Inputs text Max sequence length 8,192
Benchmarks Duplicate question detection from AskUbuntu
Corpus: 6,743 Queries: 360
Quality
ndcg at 10 0.6388
map at 10 0.4817
mrr at 10 0.7277
Reference →
Quality
ndcg at 10 0.4673
map at 10 0.4037
mrr at 10 0.4918
Quality
ndcg at 10 0.4864
map at 10 0.4193
mrr at 10 0.5036
Duplicate question retrieval from StackExchange Physics
Corpus: 38,314 Queries: 1,039
Performance L4-SPOT b1 c16
Corpus 1.9K tok/s
Corpus p50 509.4ms
Query 131 tok/s
Query p50 573.4ms
Performance L4 b1 c16
Corpus 1.9K tok/s
Corpus p50 509.4ms
Query 131 tok/s
Query p50 573.4ms
Reference →
Code search with natural language queries
Corpus: 6,267 Queries: 500
Performance L4-SPOT b1 c16
Corpus 890 tok/s
Corpus p50 454.2ms
Query 75 tok/s
Query p50 566.6ms
Performance L4 b1 c16
Corpus 890 tok/s
Corpus p50 454.2ms
Query 75 tok/s
Query p50 566.6ms
Reference →
Financial opinion mining and question answering
Corpus: 57,599 Queries: 648
Performance L4-SPOT b1 c16
Corpus 2.6K tok/s
Corpus p50 469.6ms
Query 303 tok/s
Query p50 278.2ms
Performance L4 b1 c16
Corpus 2.6K tok/s
Corpus p50 469.6ms
Query 303 tok/s
Query p50 278.2ms
Reference →
Question answering on consumer contracts
Corpus: 153 Queries: 396
Performance L4-SPOT b1 c16
Corpus 6.2K tok/s
Corpus p50 532.8ms
Query 278 tok/s
Query p50 327.3ms
Performance L4 b1 c16
Corpus 6.2K tok/s
Corpus p50 532.8ms
Query 278 tok/s
Query p50 327.3ms
Reference →
Multilingual MARCO passage reranking (Chinese)
Quality
ndcg at 10 0.2453
map at 10 0.2024
mrr at 10 0.2072
Reference →
Biomedical literature search from NutritionFacts.org
Corpus: 3,593 Queries: 323
Performance L4-SPOT b1 c16
Corpus 4.4K tok/s
Corpus p50 463.3ms
Query 111 tok/s
Query p50 299.7ms
Performance L4 b1 c16
Corpus 4.4K tok/s
Corpus p50 463.3ms
Query 111 tok/s
Query p50 299.7ms
Reference →
Citation prediction, document classification, and recommendation for scientific papers
Corpus: 25,656 Queries: 1,000
Performance L4-SPOT b1 c16
Corpus 4.4K tok/s
Corpus p50 257.6ms
Query 184 tok/s
Query p50 327.2ms
Performance L4 b1 c16
Corpus 4.4K tok/s
Corpus p50 257.6ms
Query 184 tok/s
Query p50 327.2ms
Reference →
Scientific claim verification using research literature
Corpus: 5,183 Queries: 300
Performance L4-SPOT b1 c16
Corpus 9.2K tok/s
Corpus p50 241.6ms
Query 396 tok/s
Query p50 265.9ms
Performance L4 b1 c16
Corpus 9.2K tok/s
Corpus p50 241.6ms
Query 396 tok/s
Query p50 265.9ms
Reference →
Programming question answering from Stack Overflow
Corpus: 19,931 Queries: 1,994
Performance L4-SPOT b1 c16
Corpus 3.8K tok/s
Corpus p50 458.1ms
Query 9.2K tok/s
Query p50 222.9ms
Performance L4 b1 c16
Corpus 3.8K tok/s
Corpus p50 458.1ms
Query 9.2K tok/s
Query p50 222.9ms
Reference →
