Instructions to use nebhailema/afrixir-multivector-e5-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use nebhailema/afrixir-multivector-e5-base with sentence-transformers:
from sentence_transformers import MultiVectorEncoder model = MultiVectorEncoder("nebhailema/afrixir-multivector-e5-base") queries = ["Which planet is known as the Red Planet?"] documents = [ "Venus is often called Earth's twin because of its similar size and proximity.", "Mars, known for its reddish appearance, is often referred to as the Red Planet.", "Jupiter, the largest planet in our solar system, has a prominent red spot.", ] query_embeddings = model.encode_query(queries) document_embeddings = model.encode_document(documents) similarities = model.similarity(query_embeddings, document_embeddings) print(similarities) - Notebooks
- Google Colab
- Kaggle
AfriXIR multi-vector retriever
This is a Multi-Vector Encoder model finetuned from intfloat/multilingual-e5-base on the AfriXIR dataset using the sentence-transformers library. It maps inputs to sequences of 128-dimensional token-level vectors and scores them with late interaction (MaxSim), useful for passage retrieval.
Model Details
Model Description
- Model Type: Multi-Vector Encoder
- Base model: intfloat/multilingual-e5-base
- Maximum Sequence Length: 512 tokens
- Maximum Query Length: 512 tokens
- Maximum Document Length: 512 tokens
- Output Dimensionality: 128 dimensions
- Similarity Function: MaxSim
- Supported Modality: Text
- Training Dataset:
- Languages: am, ha, om, sn, so, sw, yo, zu
- License: apache-2.0
Model Sources
- Documentation: Sentence Transformers Documentation
- Documentation: Multi-Vector Encoder Documentation
- Repository: Sentence Transformers on GitHub
- Hugging Face: Multi-Vector Encoders on Hugging Face
Full Model Architecture
MultiVectorEncoder(
(0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'query_length': 512, 'document_length': 512, 'architecture': 'XLMRobertaModel'})
(1): Dense({'in_features': 768, 'out_features': 128, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity', 'module_input_name': 'token_embeddings', 'module_output_name': 'token_embeddings'})
(2): MultiVectorMask({'skiplist_words': ['!', '"', '#', '$', '%', '&', "'", '(', ')', '*', '+', ',', '-', '.', '/', ':', ';', '<', '=', '>', '?', '@', '[', '\\', ']', '^', '_', '`', '{', '|', '}', '~'], 'skiplist_tasks': ['document'], 'keep_only_token_ids': None})
(3): Normalize({'module_input_name': 'token_embeddings', 'module_output_name': 'token_embeddings'})
)
Usage
Direct Usage (Sentence Transformers)
First install the Sentence Transformers library:
pip install -U sentence-transformers
Then you can load this model and run inference.
from sentence_transformers import MultiVectorEncoder
# Download from the 🤗 Hub
model = MultiVectorEncoder("nebhailema/afrixir-multivector-e5-base")
# Run inference: each input becomes a sequence of per-token vectors (variable length).
queries = [
'ስሩዕ ክብድን ዝበለ ልምምድ ኤሮቢክስ ምዝውታር ኣካላትና እንታይ ክንረክብ ይሕግዘና?',
]
documents = [
'ስሩዕን ክብድን ዝበለ ልምምድ ኤሮቢክስ ምዝውታር ኣካላትና እኹል ኦክስጅን ክንረክብ ይሕግዘና። ‘adenosine triphosphate’ ዝተባህለ ጥረ ነገር ብብዝሒ ኣብ ዋህዮታት ጭዋዳታትና ክፈሪ ይርአ። ‘adenosine triphosphate’ ጭዋዳታትና እኹል ጸዓት/ ሓይሊ ንኽረክብ ዝሕግዝ ባእታ’ዩ። ብኡኡ ኣቢሉ’ውን ደምና እኹል ኦክስጅን ይረክብ። በንጻሩ ውሑድ ‘adenosine triphosphate’ ዘፍሪ ሰብ ቀጻሊ ኣካላዊ ስንፈት/ ድኻም ይረኣዮ። እኹል ሰብ ኣብ ሰሙን ካብ 3 ክሳብ 5 ግዜ ብዘይ ምቁራጽ 15 ደቓይቕ ዝከውን ልምምድ ኤሮቢክስ ምስ ዘካይድ እኹል’ዩ። ዕድሚኦም ልዕሊ 35 ዓመት ዝኹኑ ደቂተባዕትዮ ይኹኒ ደቀኣንስትዮ ቅድሚ ምጅማር መደብ ልምምድ ኤሮቢክስ፡ ሕክምናዊ መርመራ ከካይዱ/ ከካይዳ ከምዘለዎም/ ከምዘለወን ክኢላታት ይመኽሩ።',
'እታ ነዊሕ እትጓዓዝ ዑፍ - ኣልባጥሮስ\nዝዝምብያ ኣዕዋፍ፡ ብሒደት ጕልበት እየን ኣብ ኣየር ዝንሳፈፋ። እታ ነዊሕ ጕዕዞ እትጓዓዝ ኣልባጥሮስ ከኣ፡ ዝበለጸት ኣብነት’ያ። እዛ ዑፍ እዝኣ፡ 3.4 ሜተር ዝንውሓቱ ኣኽናፍ ዘለዋን 8.5 ኪሎ ግራም ዝኽብደታን ኰይና፡ ብዙሕ ጕልበት ከይተጠቕመት ንኣሽሓት ኪሎ ሜትራት ክትበርር ትኽእል እያ። ከምኡ ኽትገብር ዝኸኣለት፡ ሳላ ቕርጺ ሰብነታን ሳላ እቲ እትዝምብየሉ መገድን እዩ። ነዝ ዝስዕብ ሕሰበሉ፦ እታ ዑፍ ክትበርር ከላን ንኣኽናፋ ምሉእ ብምሉእ ክትዝርግሖ ኸላን፡ ንኣኽናፋ ኣሲሩ ዝሕዞ ፍሉይ ጅማት ትጥቀም እያ። እዝ ኸኣ ጭዋዳታታ ንኸይደክም ይሕግዛ እዩ። ብዘይካ’ዝ፡ ንነዊሕ ሰዓታት ክትዝምቢ እትኽእል፡ ነቲ ኻብ ውቅያኖሳት ዝመጽእ ንፋስ ብውሕልነት ስለ እትጥቀመሉ’ያ።',
'ሰሪ ኣ\nግጥማት ሰሪ ኣ ኢጣልያ ብቐዳም ኣብ ዝቐጸለሉ፡ ሮማ ክልተ ነጥቢ ከሲራ። ሮማ ምስ መራሒት ዘላ ጁቬንቱስ ናይ ሽዱሽተ ነጥቢ ፍልልይ እዩ ዘለዋ። ነዚ ንምጽባብ ብቐዳም ኣንጻር ኢምፖሊ ተጻዊታ ብምዕዋት፡ ኣብ ልዕሊ እታ ሰንበት ምስ ኡዲነዘ እትገጥም ጁቬንቱስ ጸቕጢ ክትፈጥር ትኽእሎ ነርዋ። ይኹን እምበር ሮማ ኣብ ሜዳኣ ምስ ኢምፓሊ 1ብ1 ብምፍልላያ ነቲ ዕድል ኣባኺናቶ። ሮማ ሳልሳይ ተኸታታሊ ጸወታኣ ነጥቢ ተማቒላ ትወጽእ ብምህላዋ፡ ጁቬቱስ መሪሕነት ሰሪ ኣ ኢጣልያ ቀሲና ክትቅልሶ ኣኽኢልዋ ኣሎ።\n\nብዘይካዚ ብቐዳም ጀኖኣ ምስ ፊዮረንቲና 1ብ1 ተፈላልየን። ዝበዝሕ ግጥማት’ቲ ሊግ ትማሊ ሰንበት እዩ ተኻይዱ።\n\nጁቬንቱስ ሓደ ጸወታ ካብ ሮማ ድሒራ ብ49 ነጥቢ ቀዳመይቲ፡ ሮማ ብ43 ነጥቢ ካልኣይቲ ናፖሊ ብ36 ነጥቢ ሳልሰይቲ ኮይነን ይመርሓ።',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings[0].shape, document_embeddings[0].shape)
# (41, 128) (306, 128)
# Get the MaxSim similarity scores
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[35.1270, 19.4954, 17.0075]])
Evaluation
Full-corpus passage retrieval on AfriXIR for Amharic, Hausa, Oromo, Shona, Somali, Swahili, Tigrinya, and Yoruba. avg is the query-weighted average across those languages. The best value in that column is bold.
Reranker rows rerank the top 50 passages from a frozen dense retriever.
Multivector
Multivector retrievers compared with each other on recall@5, recall@10, nDCG@10, and MRR@10.
recall@5
| model | amharic | hausa | oromo | shona | somali | swahili | tigrinya | yoruba | avg |
|---|---|---|---|---|---|---|---|---|---|
| multivector mini | 0.8710 | 0.8177 | 0.8126 | 0.8162 | 0.8358 | 0.8311 | 0.9388 | 0.7841 | 0.8471 |
| multivector e5-small | 0.8868 | 0.8204 | 0.7832 | 0.8108 | 0.8515 | 0.8662 | 0.8980 | 0.7691 | 0.8578 |
| multivector e5-base | 0.9034 | 0.8718 | 0.8246 | 0.8432 | 0.8695 | 0.8719 | 0.9388 | 0.7922 | 0.8789 |
| M3 multi | 0.8485 | 0.7960 | 0.7919 | 0.8649 | 0.8211 | 0.8260 | 0.9184 | 0.7108 | 0.8246 |
recall@10
| model | amharic | hausa | oromo | shona | somali | swahili | tigrinya | yoruba | avg |
|---|---|---|---|---|---|---|---|---|---|
| multivector mini | 0.9008 | 0.8809 | 0.8725 | 0.8541 | 0.8898 | 0.8802 | 0.9388 | 0.8323 | 0.8877 |
| multivector e5-small | 0.9183 | 0.8755 | 0.8573 | 0.8757 | 0.9033 | 0.9146 | 0.9592 | 0.8102 | 0.8995 |
| multivector e5-base | 0.9300 | 0.9206 | 0.8758 | 0.8649 | 0.9123 | 0.9152 | 0.9388 | 0.8394 | 0.9140 |
| M3 multi | 0.8896 | 0.8484 | 0.8529 | 0.8865 | 0.8763 | 0.8878 | 0.9388 | 0.7751 | 0.8732 |
ndcg@10
| model | amharic | hausa | oromo | shona | somali | swahili | tigrinya | yoruba | avg |
|---|---|---|---|---|---|---|---|---|---|
| multivector mini | 0.8028 | 0.7163 | 0.7364 | 0.7599 | 0.7551 | 0.7352 | 0.8785 | 0.6876 | 0.7690 |
| multivector e5-small | 0.8272 | 0.7280 | 0.7167 | 0.7688 | 0.7617 | 0.7801 | 0.8876 | 0.6858 | 0.7880 |
| multivector e5-base | 0.8428 | 0.7853 | 0.7429 | 0.7801 | 0.7867 | 0.7989 | 0.8569 | 0.7137 | 0.8098 |
| M3 multi | 0.7690 | 0.6967 | 0.7113 | 0.7824 | 0.7315 | 0.7365 | 0.8879 | 0.6265 | 0.7410 |
mrr@10
| model | amharic | hausa | oromo | shona | somali | swahili | tigrinya | yoruba | avg |
|---|---|---|---|---|---|---|---|---|---|
| multivector mini | 0.7709 | 0.6631 | 0.6930 | 0.7291 | 0.7118 | 0.6884 | 0.8571 | 0.6407 | 0.7305 |
| multivector e5-small | 0.7977 | 0.6803 | 0.6723 | 0.7352 | 0.7160 | 0.7366 | 0.8652 | 0.6452 | 0.7520 |
| multivector e5-base | 0.8145 | 0.7413 | 0.7000 | 0.7524 | 0.7459 | 0.7612 | 0.8296 | 0.6731 | 0.7760 |
| M3 multi | 0.7296 | 0.6476 | 0.6660 | 0.7481 | 0.6850 | 0.6880 | 0.8716 | 0.5789 | 0.6982 |
All models
Dense, sparse, multivector, and reranker models compared with each other on recall@5, recall@10, nDCG@10, and MRR@10.
recall@5
| model | amharic | hausa | oromo | shona | somali | swahili | tigrinya | yoruba | avg |
|---|---|---|---|---|---|---|---|---|---|
| dense mini | 0.7805 | 0.6940 | 0.5643 | 0.6270 | 0.6637 | 0.7081 | 0.7755 | 0.6024 | 0.7233 |
| e5-small | 0.8741 | 0.8014 | 0.7418 | 0.8162 | 0.8088 | 0.8451 | 0.8571 | 0.7359 | 0.8379 |
| e5-base | 0.8886 | 0.8691 | 0.7810 | 0.8000 | 0.8526 | 0.8738 | 0.8571 | 0.7590 | 0.8629 |
| e5-large | 0.8948 | 0.8809 | 0.7974 | 0.8324 | 0.8841 | 0.8993 | 0.7755 | 0.7550 | 0.8738 |
| M3 dense | 0.7067 | 0.6264 | 0.4630 | 0.5892 | 0.5894 | 0.6488 | 0.7551 | 0.5231 | 0.6501 |
| SPLADE mini | 0.7759 | 0.7446 | 0.7603 | 0.7405 | 0.7705 | 0.7546 | 0.8163 | 0.6657 | 0.7599 |
| M3 sparse | 0.7826 | 0.7356 | 0.7593 | 0.7189 | 0.7627 | 0.7463 | 0.8367 | 0.6536 | 0.7598 |
| multivector mini | 0.8710 | 0.8177 | 0.8126 | 0.8162 | 0.8358 | 0.8311 | 0.9388 | 0.7841 | 0.8471 |
| multivector e5-small | 0.8868 | 0.8204 | 0.7832 | 0.8108 | 0.8515 | 0.8662 | 0.8980 | 0.7691 | 0.8578 |
| multivector e5-base | 0.9034 | 0.8718 | 0.8246 | 0.8432 | 0.8695 | 0.8719 | 0.9388 | 0.7922 | 0.8789 |
| M3 multi | 0.8485 | 0.7960 | 0.7919 | 0.8649 | 0.8211 | 0.8260 | 0.9184 | 0.7108 | 0.8246 |
| reranker mini | 0.8647 | 0.8159 | 0.7462 | 0.7946 | 0.8245 | 0.8305 | 0.9184 | 0.7359 | 0.8336 |
| reranker e5-small | 0.8907 | 0.8430 | 0.8279 | 0.8541 | 0.8673 | 0.8693 | 0.9592 | 0.7871 | 0.8690 |
| reranker e5-base | 0.9082 | 0.8727 | 0.8497 | 0.8486 | 0.8943 | 0.8725 | 0.8980 | 0.7932 | 0.8853 |
recall@10
| model | amharic | hausa | oromo | shona | somali | swahili | tigrinya | yoruba | avg |
|---|---|---|---|---|---|---|---|---|---|
| dense mini | 0.8285 | 0.7644 | 0.6362 | 0.6973 | 0.7334 | 0.7827 | 0.8163 | 0.6737 | 0.7820 |
| e5-small | 0.9072 | 0.8718 | 0.8007 | 0.8811 | 0.8774 | 0.9012 | 0.8980 | 0.7982 | 0.8844 |
| e5-base | 0.9209 | 0.9070 | 0.8410 | 0.8649 | 0.9224 | 0.9133 | 0.8571 | 0.8233 | 0.9042 |
| e5-large | 0.9273 | 0.9242 | 0.8551 | 0.8811 | 0.9359 | 0.9344 | 0.8163 | 0.8143 | 0.9131 |
| M3 dense | 0.7584 | 0.6931 | 0.5381 | 0.6595 | 0.6704 | 0.7208 | 0.7755 | 0.5944 | 0.7112 |
| SPLADE mini | 0.8293 | 0.7924 | 0.8115 | 0.8162 | 0.8425 | 0.8317 | 0.8776 | 0.7440 | 0.8192 |
| M3 sparse | 0.8279 | 0.8087 | 0.8137 | 0.8000 | 0.8256 | 0.8107 | 0.8776 | 0.7169 | 0.8138 |
| multivector mini | 0.9008 | 0.8809 | 0.8725 | 0.8541 | 0.8898 | 0.8802 | 0.9388 | 0.8323 | 0.8877 |
| multivector e5-small | 0.9183 | 0.8755 | 0.8573 | 0.8757 | 0.9033 | 0.9146 | 0.9592 | 0.8102 | 0.8995 |
| multivector e5-base | 0.9300 | 0.9206 | 0.8758 | 0.8649 | 0.9123 | 0.9152 | 0.9388 | 0.8394 | 0.9140 |
| M3 multi | 0.8896 | 0.8484 | 0.8529 | 0.8865 | 0.8763 | 0.8878 | 0.9388 | 0.7751 | 0.8732 |
| reranker mini | 0.8872 | 0.8547 | 0.7800 | 0.8324 | 0.8605 | 0.8662 | 0.9592 | 0.7620 | 0.8615 |
| reranker e5-small | 0.9206 | 0.8917 | 0.8704 | 0.8811 | 0.9168 | 0.9191 | 0.9592 | 0.8414 | 0.9072 |
| reranker e5-base | 0.9345 | 0.9224 | 0.8987 | 0.8919 | 0.9314 | 0.9344 | 0.9592 | 0.8454 | 0.9229 |
ndcg@10
| model | amharic | hausa | oromo | shona | somali | swahili | tigrinya | yoruba | avg |
|---|---|---|---|---|---|---|---|---|---|
| dense mini | 0.7129 | 0.5933 | 0.4881 | 0.5533 | 0.5709 | 0.6234 | 0.6532 | 0.5160 | 0.6464 |
| e5-small | 0.8086 | 0.7077 | 0.6464 | 0.7233 | 0.7270 | 0.7653 | 0.7810 | 0.6609 | 0.7635 |
| e5-base | 0.8264 | 0.7661 | 0.6851 | 0.7362 | 0.7691 | 0.7929 | 0.7583 | 0.6855 | 0.7897 |
| e5-large | 0.8294 | 0.7962 | 0.7089 | 0.7499 | 0.8061 | 0.8147 | 0.7093 | 0.6677 | 0.7997 |
| M3 dense | 0.6340 | 0.5278 | 0.4034 | 0.5053 | 0.5045 | 0.5699 | 0.6650 | 0.4406 | 0.5734 |
| SPLADE mini | 0.6816 | 0.6213 | 0.6629 | 0.6763 | 0.6768 | 0.6579 | 0.7696 | 0.5729 | 0.6633 |
| M3 sparse | 0.6987 | 0.6469 | 0.6776 | 0.6599 | 0.6835 | 0.6593 | 0.7754 | 0.5562 | 0.6750 |
| multivector mini | 0.8028 | 0.7163 | 0.7364 | 0.7599 | 0.7551 | 0.7352 | 0.8785 | 0.6876 | 0.7690 |
| multivector e5-small | 0.8272 | 0.7280 | 0.7167 | 0.7688 | 0.7617 | 0.7801 | 0.8876 | 0.6858 | 0.7880 |
| multivector e5-base | 0.8428 | 0.7853 | 0.7429 | 0.7801 | 0.7867 | 0.7989 | 0.8569 | 0.7137 | 0.8098 |
| M3 multi | 0.7690 | 0.6967 | 0.7113 | 0.7824 | 0.7315 | 0.7365 | 0.8879 | 0.6265 | 0.7410 |
| reranker mini | 0.8082 | 0.7483 | 0.6906 | 0.7416 | 0.7613 | 0.7523 | 0.8987 | 0.6671 | 0.7722 |
| reranker e5-small | 0.8284 | 0.7397 | 0.7435 | 0.7852 | 0.7814 | 0.7815 | 0.9037 | 0.6999 | 0.7946 |
| reranker e5-base | 0.8449 | 0.7681 | 0.7668 | 0.7903 | 0.7968 | 0.7947 | 0.8769 | 0.7018 | 0.8107 |
mrr@10
| model | amharic | hausa | oromo | shona | somali | swahili | tigrinya | yoruba | avg |
|---|---|---|---|---|---|---|---|---|---|
| dense mini | 0.6759 | 0.5387 | 0.4412 | 0.5077 | 0.5192 | 0.5729 | 0.6004 | 0.4658 | 0.6032 |
| e5-small | 0.7766 | 0.6548 | 0.5970 | 0.6736 | 0.6790 | 0.7214 | 0.7437 | 0.6169 | 0.7246 |
| e5-base | 0.7957 | 0.7201 | 0.6350 | 0.6957 | 0.7202 | 0.7534 | 0.7245 | 0.6418 | 0.7527 |
| e5-large | 0.7976 | 0.7544 | 0.6620 | 0.7077 | 0.7643 | 0.7756 | 0.6741 | 0.6208 | 0.7629 |
| M3 dense | 0.5941 | 0.4746 | 0.3609 | 0.4563 | 0.4518 | 0.5221 | 0.6291 | 0.3917 | 0.5295 |
| SPLADE mini | 0.6338 | 0.5656 | 0.6148 | 0.6319 | 0.6237 | 0.6027 | 0.7358 | 0.5185 | 0.6130 |
| M3 sparse | 0.6568 | 0.5950 | 0.6337 | 0.6157 | 0.6376 | 0.6108 | 0.7417 | 0.5047 | 0.6302 |
| multivector mini | 0.7709 | 0.6631 | 0.6930 | 0.7291 | 0.7118 | 0.6884 | 0.8571 | 0.6407 | 0.7305 |
| multivector e5-small | 0.7977 | 0.6803 | 0.6723 | 0.7352 | 0.7160 | 0.7366 | 0.8652 | 0.6452 | 0.7520 |
| multivector e5-base | 0.8145 | 0.7413 | 0.7000 | 0.7524 | 0.7459 | 0.7612 | 0.8296 | 0.6731 | 0.7760 |
| M3 multi | 0.7296 | 0.6476 | 0.6660 | 0.7481 | 0.6850 | 0.6880 | 0.8716 | 0.5789 | 0.6982 |
| reranker mini | 0.7824 | 0.7139 | 0.6618 | 0.7122 | 0.7296 | 0.7152 | 0.8793 | 0.6361 | 0.7431 |
| reranker e5-small | 0.7984 | 0.6900 | 0.7023 | 0.7539 | 0.7379 | 0.7369 | 0.8850 | 0.6541 | 0.7580 |
| reranker e5-base | 0.8156 | 0.7178 | 0.7240 | 0.7572 | 0.7527 | 0.7498 | 0.8509 | 0.6553 | 0.7741 |
Training Details
Training Dataset
AfriXIR
- Dataset: AfriXIR
- Size: 112,864 training samples
- Columns:
anchor,positive,negative_0,negative_1,negative_2,negative_3,negative_4,negative_5,negative_6, andnegative_7
Evaluation Dataset
AfriXIR
- Dataset: AfriXIR
- Size: 12,546 evaluation samples
- Columns:
anchor,positive,negative_0,negative_1,negative_2,negative_3,negative_4,negative_5,negative_6, andnegative_7
Citation
BibTeX
Sentence Transformers
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/1908.10084",
}
CachedMultiVectorMultipleNegativesRankingLoss
@misc{gao2021scaling,
title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup},
author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan},
year={2021},
eprint={2101.06983},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
- Downloads last month
- 3
Model tree for nebhailema/afrixir-multivector-e5-base
Base model
intfloat/multilingual-e5-base