fastembed/docs/examples/Supported_Models.ipynb

In [1]:

%load_ext autoreload
%autoreload 2

In [ ]:

import pandas as pd

from fastembed import SparseTextEmbedding, TextEmbedding

Supported Text Embedding Models

In [2]:

supported_models = (
    pd.DataFrame(TextEmbedding.list_supported_models())
    .sort_values("size_in_GB")
    .drop(columns="sources")
    .reset_index(drop=True)
)
supported_models

Out [2]:

	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	sentence-transformers/all-MiniLM-L6-v2	384	Sentence Transformer model, MiniLM-L6-v2	0.090
3	snowflake/snowflake-arctic-embed-xs	384	Based on all-MiniLM-L6-v2 model with only 22m ...	0.090
4	jinaai/jina-embeddings-v2-small-en	512	English embedding model supporting 8192 sequen...	0.120
5	snowflake/snowflake-arctic-embed-s	384	Based on infloat/e5-small-unsupervised, does n...	0.130
6	BAAI/bge-small-en	384	Fast English model	0.130
7	BAAI/bge-base-en-v1.5	768	Base English model, v1.5	0.210
8	sentence-transformers/paraphrase-multilingual-...	384	Sentence Transformer model, paraphrase-multili...	0.220
9	BAAI/bge-base-en	768	Base English model	0.420
10	snowflake/snowflake-arctic-embed-m	768	Based on intfloat/e5-base-unsupervised model, ...	0.430
11	jinaai/jina-embeddings-v2-base-en	768	English embedding model supporting 8192 sequen...	0.520
12	nomic-ai/nomic-embed-text-v1	768	8192 context length english model	0.520
13	nomic-ai/nomic-embed-text-v1.5	768	8192 context length english model	0.520
14	snowflake/snowflake-arctic-embed-m-long	768	Based on nomic-ai/nomic-embed-text-v1-unsuperv...	0.540
15	mixedbread-ai/mxbai-embed-large-v1	1024	MixedBread Base sentence embedding model, does...	0.640
16	sentence-transformers/paraphrase-multilingual-...	768	Sentence-transformers model for tasks like clu...	1.000
17	snowflake/snowflake-arctic-embed-l	1024	Based on intfloat/e5-large-unsupervised, large...	1.020
18	BAAI/bge-large-en-v1.5	1024	Large English model, v1.5	1.200
19	thenlper/gte-large	1024	Large general text embeddings model	1.200
20	intfloat/multilingual-e5-large	1024	Multilingual model, e5-large. Recommend using ...	2.240

Supported Sparse Text Embedding Models

In [7]:

pd.DataFrame(SparseTextEmbedding.list_supported_models())

Out [7]:

	model	vocab_size	description	size_in_GB	sources
0	prithvida/Splade_PP_en_v1	30522	Misspelled version of the model. Retained for ...	0.532	{'hf': 'Qdrant/SPLADE_PP_en_v1'}
1	prithivida/Splade_PP_en_v1	30522	Independent Implementation of SPLADE++ Model f...	0.532	{'hf': 'Qdrant/SPLADE_PP_en_v1'}