fastembed/docs/examples/Supported_Models.ipynb

In [4]:

%load_ext autoreload
%autoreload 2

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

In [ ]:

import pandas as pd

from fastembed import (
    SparseTextEmbedding,
    TextEmbedding,
    LateInteractionTextEmbedding,
    ImageEmbedding,
)

Supported Text Embedding Models

In [5]:

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 [5]:

	model	dim	description	size_in_GB
0	BAAI/bge-small-en-v1.5	384	Fast and Default English model	0.067
1	BAAI/bge-small-zh-v1.5	512	Fast and recommended Chinese model	0.090
2	snowflake/snowflake-arctic-embed-xs	384	Based on all-MiniLM-L6-v2 model with only 22m ...	0.090
3	sentence-transformers/all-MiniLM-L6-v2	384	Sentence Transformer model, MiniLM-L6-v2	0.090
4	jinaai/jina-embeddings-v2-small-en	512	English embedding model supporting 8192 sequen...	0.120
5	BAAI/bge-small-en	384	Fast English model	0.130
6	snowflake/snowflake-arctic-embed-s	384	Based on infloat/e5-small-unsupervised, does n...	0.130
7	nomic-ai/nomic-embed-text-v1.5-Q	768	Quantized 8192 context length english model	0.130
8	BAAI/bge-base-en-v1.5	768	Base English model, v1.5	0.210
9	sentence-transformers/paraphrase-multilingual-...	384	Sentence Transformer model, paraphrase-multili...	0.220
10	Qdrant/clip-ViT-B-32-text	512	CLIP text encoder	0.250
11	jinaai/jina-embeddings-v2-base-de	768	German embedding model supporting 8192 sequenc...	0.320
12	BAAI/bge-base-en	768	Base English model	0.420
13	snowflake/snowflake-arctic-embed-m	768	Based on intfloat/e5-base-unsupervised model, ...	0.430
14	nomic-ai/nomic-embed-text-v1.5	768	8192 context length english model	0.520
15	jinaai/jina-embeddings-v2-base-en	768	English embedding model supporting 8192 sequen...	0.520
16	nomic-ai/nomic-embed-text-v1	768	8192 context length english model	0.520
17	snowflake/snowflake-arctic-embed-m-long	768	Based on nomic-ai/nomic-embed-text-v1-unsuperv...	0.540
18	mixedbread-ai/mxbai-embed-large-v1	1024	MixedBread Base sentence embedding model, does...	0.640
19	jinaai/jina-embeddings-v2-base-code	768	Source code embedding model supporting 8192 se...	0.640
20	sentence-transformers/paraphrase-multilingual-...	768	Sentence-transformers model for tasks like clu...	1.000
21	snowflake/snowflake-arctic-embed-l	1024	Based on intfloat/e5-large-unsupervised, large...	1.020
22	thenlper/gte-large	1024	Large general text embeddings model	1.200
23	BAAI/bge-large-en-v1.5	1024	Large English model, v1.5	1.200
24	intfloat/multilingual-e5-large	1024	Multilingual model, e5-large. Recommend using ...	2.240

Supported Sparse Text Embedding Models

In [4]:

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

Out [4]:

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

Supported Late Interaction Text Embedding Models

In [5]:

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

Out [5]:

	model	dim	description	size_in_GB
0	colbert-ir/colbertv2.0	128	Late interaction model	0.44

Supported Image Embedding Models

In [6]:

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

Out [6]:

	model	dim	description	size_in_GB
0	Qdrant/resnet50-onnx	2048	ResNet-50 from `Deep Residual Learning for Ima...	0.10
1	Qdrant/clip-ViT-B-32-vision	512	CLIP vision encoder based on ViT-B/32	0.34
2	Qdrant/Unicom-ViT-B-32	512	Unicom Unicom-ViT-B-32 from open-metric-learning	0.48
3	Qdrant/Unicom-ViT-B-16	768	Unicom Unicom-ViT-B-16 from open-metric-learning	0.82