fastembed/docs/examples/Supported_Models.ipynb

In [10]:

%load_ext autoreload
%autoreload 2

The autoreload extension is already loaded. To reload it, use:
  %reload_ext autoreload

In [11]:

import pandas as pd

from fastembed import (
    SparseTextEmbedding,
    TextEmbedding,
    LateInteractionTextEmbedding,
    ImageEmbedding,
)
from fastembed.rerank.cross_encoder import TextCrossEncoder

Supported Text Embedding Models

In [12]:

supported_models = (
    pd.DataFrame(TextEmbedding.list_supported_models())
    .sort_values("size_in_GB")
    .drop(columns=["sources", "model_file", "additional_files"])
    .reset_index(drop=True)
)
supported_models

Out [12]:

	model	dim	description	license	size_in_GB
0	BAAI/bge-small-en-v1.5	384	Text embeddings, Unimodal (text), English, 512...	mit	0.067
1	BAAI/bge-small-zh-v1.5	512	Text embeddings, Unimodal (text), Chinese, 512...	mit	0.090
2	snowflake/snowflake-arctic-embed-xs	384	Text embeddings, Unimodal (text), English, 512...	apache-2.0	0.090
3	sentence-transformers/all-MiniLM-L6-v2	384	Text embeddings, Unimodal (text), English, 256...	apache-2.0	0.090
4	jinaai/jina-embeddings-v2-small-en	512	Text embeddings, Unimodal (text), English, 819...	apache-2.0	0.120
5	BAAI/bge-small-en	384	Text embeddings, Unimodal (text), English, 512...	mit	0.130
6	snowflake/snowflake-arctic-embed-s	384	Text embeddings, Unimodal (text), English, 512...	apache-2.0	0.130
7	nomic-ai/nomic-embed-text-v1.5-Q	768	Text embeddings, Multimodal (text, image), Eng...	apache-2.0	0.130
8	BAAI/bge-base-en-v1.5	768	Text embeddings, Unimodal (text), English, 512...	mit	0.210
9	sentence-transformers/paraphrase-multilingual-...	384	Text embeddings, Unimodal (text), Multilingual...	apache-2.0	0.220
10	Qdrant/clip-ViT-B-32-text	512	Text embeddings, Multimodal (text&image), Engl...	mit	0.250
11	jinaai/jina-embeddings-v2-base-de	768	Text embeddings, Unimodal (text), Multilingual...	apache-2.0	0.320
12	BAAI/bge-base-en	768	Text embeddings, Unimodal (text), English, 512...	mit	0.420
13	snowflake/snowflake-arctic-embed-m	768	Text embeddings, Unimodal (text), English, 512...	apache-2.0	0.430
14	nomic-ai/nomic-embed-text-v1.5	768	Text embeddings, Multimodal (text, image), Eng...	apache-2.0	0.520
15	jinaai/jina-embeddings-v2-base-en	768	Text embeddings, Unimodal (text), English, 819...	apache-2.0	0.520
16	nomic-ai/nomic-embed-text-v1	768	Text embeddings, Multimodal (text, image), Eng...	apache-2.0	0.520
17	snowflake/snowflake-arctic-embed-m-long	768	Text embeddings, Unimodal (text), English, 204...	apache-2.0	0.540
18	mixedbread-ai/mxbai-embed-large-v1	1024	Text embeddings, Unimodal (text), English, 512...	apache-2.0	0.640
19	jinaai/jina-embeddings-v2-base-code	768	Text embeddings, Unimodal (text), Multilingual...	apache-2.0	0.640
20	sentence-transformers/paraphrase-multilingual-...	768	Text embeddings, Unimodal (text), Multilingual...	apache-2.0	1.000
21	snowflake/snowflake-arctic-embed-l	1024	Text embeddings, Unimodal (text), English, 512...	apache-2.0	1.020
22	thenlper/gte-large	1024	Text embeddings, Unimodal (text), English, 512...	mit	1.200
23	BAAI/bge-large-en-v1.5	1024	Text embeddings, Unimodal (text), English, 512...	mit	1.200
24	intfloat/multilingual-e5-large	1024	Text embeddings, Unimodal (text), Multilingual...	mit	2.240

Supported Sparse Text Embedding Models

In [13]:

(
    pd.DataFrame(SparseTextEmbedding.list_supported_models())
    .sort_values("size_in_GB")
    .drop(columns=["sources", "model_file", "additional_files"])
    .reset_index(drop=True)
)

Out [13]:

	model	vocab_size	description	license	size_in_GB	requires_idf
0	Qdrant/bm25	NaN	BM25 as sparse embeddings meant to be used wit...	apache-2.0	0.010	True
1	Qdrant/bm42-all-minilm-l6-v2-attentions	30522.0	Light sparse embedding model, which assigns an...	apache-2.0	0.090	True
2	prithivida/Splade_PP_en_v1	30522.0	Independent Implementation of SPLADE++ Model f...	apache-2.0	0.532	NaN
3	prithvida/Splade_PP_en_v1	30522.0	Independent Implementation of SPLADE++ Model f...	apache-2.0	0.532	NaN

Supported Late Interaction Text Embedding Models

In [14]:

(
    pd.DataFrame(LateInteractionTextEmbedding.list_supported_models())
    .sort_values("size_in_GB")
    .drop(columns=["sources", "model_file"])
    .reset_index(drop=True)
)

Out [14]:

	model	dim	description	license	size_in_GB	additional_files
0	answerdotai/answerai-colbert-small-v1	96	Text embeddings, Unimodal (text), Multilingual...	apache-2.0	0.13	NaN
1	colbert-ir/colbertv2.0	128	Late interaction model	mit	0.44	NaN
2	jinaai/jina-colbert-v2	128	New model that expands capabilities of colbert...	cc-by-nc-4.0	2.24	[onnx/model.onnx_data]

Supported Image Embedding Models

In [15]:

(
    pd.DataFrame(ImageEmbedding.list_supported_models())
    .sort_values("size_in_GB")
    .drop(columns=["sources", "model_file"])
    .reset_index(drop=True)
)

Out [15]:

	model	dim	description	license	size_in_GB
0	Qdrant/resnet50-onnx	2048	Image embeddings, Unimodal (image), 2016 year	apache-2.0	0.10
1	Qdrant/clip-ViT-B-32-vision	512	Image embeddings, Multimodal (text&image), 202...	mit	0.34
2	Qdrant/Unicom-ViT-B-32	512	Image embeddings, Multimodal (text&image), 202...	apache-2.0	0.48
3	Qdrant/Unicom-ViT-B-16	768	Image embeddings (more detailed than Unicom-Vi...	apache-2.0	0.82

Supported Rerank Cross Encoder Models

In [16]:

(
    pd.DataFrame(TextCrossEncoder.list_supported_models())
    .sort_values("size_in_GB")
    .drop(columns=["sources", "model_file"])
    .reset_index(drop=True)
)

Out [16]:

	model	size_in_GB	description	license
0	Xenova/ms-marco-MiniLM-L-6-v2	0.08	MiniLM-L-6-v2 model optimized for re-ranking t...	apache-2.0
1	Xenova/ms-marco-MiniLM-L-12-v2	0.12	MiniLM-L-12-v2 model optimized for re-ranking ...	apache-2.0
2	jinaai/jina-reranker-v1-tiny-en	0.13	Designed for blazing-fast re-ranking with 8K c...	apache-2.0
3	jinaai/jina-reranker-v1-turbo-en	0.15	Designed for blazing-fast re-ranking with 8K c...	apache-2.0
4	BAAI/bge-reranker-base	1.04	BGE reranker base model for cross-encoder re-r...	mit
5	jinaai/jina-reranker-v2-base-multilingual	1.11	A multi-lingual reranker model for cross-encod...	cc-by-nc-4.0

In [ ]: