From 2e2744877860e9e74cf42b400c0d91fef37818db Mon Sep 17 00:00:00 2001 From: George Panchuk Date: Fri, 29 Mar 2024 22:09:47 +0100 Subject: [PATCH 1/5] fix: fix model sizes in supported models lists --- fastembed/text/e5_onnx_embedding.py | 2 +- fastembed/text/jina_onnx_embedding.py | 4 ++-- fastembed/text/onnx_embedding.py | 32 +++++++++++++++++---------- 3 files changed, 23 insertions(+), 15 deletions(-) diff --git a/fastembed/text/e5_onnx_embedding.py b/fastembed/text/e5_onnx_embedding.py index 29315df0..9c37174c 100644 --- a/fastembed/text/e5_onnx_embedding.py +++ b/fastembed/text/e5_onnx_embedding.py @@ -20,7 +20,7 @@ "model": "sentence-transformers/paraphrase-multilingual-mpnet-base-v2", "dim": 768, "description": "Sentence-transformers model for tasks like clustering or semantic search", - "size_in_GB": 1.11, + "size_in_GB": 1.00, "sources": { "hf": "xenova/paraphrase-multilingual-mpnet-base-v2", }, diff --git a/fastembed/text/jina_onnx_embedding.py b/fastembed/text/jina_onnx_embedding.py index 605d0b90..ef4ffec3 100644 --- a/fastembed/text/jina_onnx_embedding.py +++ b/fastembed/text/jina_onnx_embedding.py @@ -11,14 +11,14 @@ "model": "jinaai/jina-embeddings-v2-base-en", "dim": 768, "description": "English embedding model supporting 8192 sequence length", - "size_in_GB": 0.55, + "size_in_GB": 0.52, "sources": {"hf": "xenova/jina-embeddings-v2-base-en"}, }, { "model": "jinaai/jina-embeddings-v2-small-en", "dim": 512, "description": "English embedding model supporting 8192 sequence length", - "size_in_GB": 0.13, + "size_in_GB": 0.12, "sources": {"hf": "xenova/jina-embeddings-v2-small-en"}, }, ] diff --git a/fastembed/text/onnx_embedding.py b/fastembed/text/onnx_embedding.py index e376d3f8..7d8b5c2f 100644 --- a/fastembed/text/onnx_embedding.py +++ b/fastembed/text/onnx_embedding.py @@ -12,7 +12,7 @@ "model": "BAAI/bge-base-en", "dim": 768, "description": "Base English model", - "size_in_GB": 0.5, + "size_in_GB": 0.42, "sources": { "url": "https://storage.googleapis.com/qdrant-fastembed/fast-bge-base-en.tar.gz", }, @@ -21,7 +21,7 @@ "model": "BAAI/bge-base-en-v1.5", "dim": 768, "description": "Base English model, v1.5", - "size_in_GB": 0.44, + "size_in_GB": 0.21, "sources": { "url": "https://storage.googleapis.com/qdrant-fastembed/fast-bge-base-en-v1.5.tar.gz", "hf": "qdrant/bge-base-en-v1.5-onnx-q", @@ -31,7 +31,7 @@ "model": "BAAI/bge-large-en-v1.5-quantized", "dim": 1024, "description": "Large English model, v1.5", - "size_in_GB": 1.34, + "size_in_GB": 0.64, "sources": { "hf": "qdrant/bge-large-en-v1.5-onnx-q", }, @@ -40,7 +40,7 @@ "model": "BAAI/bge-large-en-v1.5", "dim": 1024, "description": "Large English model, v1.5", - "size_in_GB": 1.34, + "size_in_GB": 1.20, "sources": { "hf": "qdrant/bge-large-en-v1.5-onnx", }, @@ -49,7 +49,7 @@ "model": "BAAI/bge-small-en", "dim": 384, "description": "Fast English model", - "size_in_GB": 0.2, + "size_in_GB": 0.13, "sources": { "url": "https://storage.googleapis.com/qdrant-fastembed/BAAI-bge-small-en.tar.gz", }, @@ -72,6 +72,14 @@ "size_in_GB": 0.13, "sources": { "url": "https://storage.googleapis.com/qdrant-fastembed/fast-bge-small-en-v1.5.tar.gz", + }, + }, + { + "model": "BAAI/bge-small-en-v1.5-quantized", + "dim": 384, + "description": "Fast and Default English model", + "size_in_GB": 0.06, + "sources": { "hf": "qdrant/bge-small-en-v1.5-onnx-q", }, }, @@ -79,12 +87,12 @@ "model": "BAAI/bge-small-zh-v1.5", "dim": 512, "description": "Fast and recommended Chinese model", - "size_in_GB": 0.1, + "size_in_GB": 0.09, "sources": { "url": "https://storage.googleapis.com/qdrant-fastembed/fast-bge-small-zh-v1.5.tar.gz", }, }, - { # todo: it is not a flag embedding + { "model": "sentence-transformers/all-MiniLM-L6-v2", "dim": 384, "description": "Sentence Transformer model, MiniLM-L6-v2", @@ -98,7 +106,7 @@ "model": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2", "dim": 384, "description": "Sentence Transformer model, paraphrase-multilingual-MiniLM-L12-v2", - "size_in_GB": 0.46, + "size_in_GB": 0.22, "sources": { "hf": "qdrant/paraphrase-multilingual-MiniLM-L12-v2-onnx-Q", }, @@ -107,7 +115,7 @@ "model": "nomic-ai/nomic-embed-text-v1", "dim": 768, "description": "8192 context length english model", - "size_in_GB": 0.54, + "size_in_GB": 0.52, "sources": { "hf": "nomic-ai/nomic-embed-text-v1", }, @@ -116,7 +124,7 @@ "model": "nomic-ai/nomic-embed-text-v1.5", "dim": 768, "description": "8192 context length english model", - "size_in_GB": 0.54, + "size_in_GB": 0.52, "sources": { "hf": "nomic-ai/nomic-embed-text-v1.5", }, @@ -125,7 +133,7 @@ "model": "thenlper/gte-large", "dim": 1024, "description": "Large general text embeddings model", - "size_in_GB": 1.34, + "size_in_GB": 1.20, "sources": { "hf": "qdrant/gte-large-onnx", }, @@ -147,7 +155,7 @@ "model": "mixedbread-ai/mxbai-embed-large-v1", "dim": 1024, "description": "MixedBread Base sentence embedding model, does well on MTEB", - "size_in_GB": 1.34, + "size_in_GB": 0.64, "sources": { "hf": "mixedbread-ai/mxbai-embed-large-v1", }, From 714781709d0b74978361db9c87efe0d8e45d9a55 Mon Sep 17 00:00:00 2001 From: George Panchuk Date: Fri, 29 Mar 2024 22:15:28 +0100 Subject: [PATCH 2/5] fix: remove redundant comment --- fastembed/text/onnx_embedding.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fastembed/text/onnx_embedding.py b/fastembed/text/onnx_embedding.py index 7d8b5c2f..ceef4ece 100644 --- a/fastembed/text/onnx_embedding.py +++ b/fastembed/text/onnx_embedding.py @@ -77,7 +77,7 @@ { "model": "BAAI/bge-small-en-v1.5-quantized", "dim": 384, - "description": "Fast and Default English model", + "description": "Fast English model", "size_in_GB": 0.06, "sources": { "hf": "qdrant/bge-small-en-v1.5-onnx-q", From 60ed079c64ee6ceb9dab4f7be013aff3d439e5ba Mon Sep 17 00:00:00 2001 From: George Panchuk Date: Fri, 29 Mar 2024 22:21:06 +0100 Subject: [PATCH 3/5] fix: fix test --- tests/test_text_onnx_embeddings.py | 1 + 1 file changed, 1 insertion(+) diff --git a/tests/test_text_onnx_embeddings.py b/tests/test_text_onnx_embeddings.py index 139d92e8..be710525 100644 --- a/tests/test_text_onnx_embeddings.py +++ b/tests/test_text_onnx_embeddings.py @@ -8,6 +8,7 @@ CANONICAL_VECTOR_VALUES = { "BAAI/bge-small-en": np.array([-0.0232, -0.0255, 0.0174, -0.0639, -0.0006]), "BAAI/bge-small-en-v1.5": np.array([0.01522374, -0.02271799, 0.00860278, -0.07424029, 0.00386434]), + "BAAI/bge-small-en-v1.5-quantized": np.array([0.01522374, -0.02271799, 0.00860278, -0.07424029, 0.00386434]), "BAAI/bge-small-zh-v1.5": np.array([-0.01023294, 0.07634465, 0.0691722, -0.04458365, -0.03160762]), "BAAI/bge-base-en": np.array([0.0115, 0.0372, 0.0295, 0.0121, 0.0346]), "BAAI/bge-base-en-v1.5": np.array([0.01129394, 0.05493144, 0.02615099, 0.00328772, 0.02996045]), From 9cb724e554bf6b3c68f7bd99ac47d05ba35bb552 Mon Sep 17 00:00:00 2001 From: George Panchuk Date: Sat, 30 Mar 2024 12:19:35 +0100 Subject: [PATCH 4/5] fix: update supported models notebook --- docs/examples/Supported_Models.ipynb | 274 +++------------------------ 1 file changed, 25 insertions(+), 249 deletions(-) diff --git a/docs/examples/Supported_Models.ipynb b/docs/examples/Supported_Models.ipynb index 98460b69..a8033812 100644 --- a/docs/examples/Supported_Models.ipynb +++ b/docs/examples/Supported_Models.ipynb @@ -2,8 +2,13 @@ "cells": [ { "cell_type": "code", - "execution_count": 2, - "metadata": {}, + "execution_count": 1, + "metadata": { + "ExecuteTime": { + "end_time": "2024-03-30T11:18:52.052764Z", + "start_time": "2024-03-30T11:18:52.039616Z" + } + }, "outputs": [], "source": [ "%load_ext autoreload\n", @@ -12,257 +17,20 @@ }, { "cell_type": "code", - "execution_count": 1, - "metadata": {}, + "execution_count": 3, + "metadata": { + "ExecuteTime": { + "end_time": "2024-03-30T11:19:01.564291Z", + "start_time": "2024-03-30T11:19:01.538768Z" + } + }, "outputs": [ { "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
modeldimdescriptionsize_in_GBsources
0BAAI/bge-base-en768Base English model0.50{'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-bge-base-en.tar.gz'}
1BAAI/bge-base-en-v1.5768Base English model, v1.50.44{'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-bge-base-en-v1.5.tar.gz', 'hf': 'qdrant/bge-base-en-v1.5-onnx-q'}
2BAAI/bge-large-en-v1.5-quantized1024Large English model, v1.51.34{'hf': 'qdrant/bge-large-en-v1.5-onnx-q'}
3BAAI/bge-large-en-v1.51024Large English model, v1.51.34{'hf': 'qdrant/bge-large-en-v1.5-onnx'}
4BAAI/bge-small-en384Fast English model0.20{'url': 'https://storage.googleapis.com/qdrant-fastembed/BAAI-bge-small-en.tar.gz'}
5BAAI/bge-small-en-v1.5384Fast and Default English model0.13{'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-bge-small-en-v1.5.tar.gz', 'hf': 'qdrant/bge-small-en-v1.5-onnx-q'}
6BAAI/bge-small-zh-v1.5512Fast and recommended Chinese model0.10{'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-bge-small-zh-v1.5.tar.gz'}
7sentence-transformers/all-MiniLM-L6-v2384Sentence Transformer model, MiniLM-L6-v20.09{'url': 'https://storage.googleapis.com/qdrant-fastembed/sentence-transformers-all-MiniLM-L6-v2.tar.gz', 'hf': 'qdrant/all-MiniLM-L6-v2-onnx'}
8sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2384Sentence Transformer model, paraphrase-multilingual-MiniLM-L12-v20.46{'hf': 'qdrant/paraphrase-multilingual-MiniLM-L12-v2-onnx-Q'}
9nomic-ai/nomic-embed-text-v17688192 context length english model0.54{'hf': 'nomic-ai/nomic-embed-text-v1'}
10nomic-ai/nomic-embed-text-v1.57688192 context length english model0.54{'hf': 'nomic-ai/nomic-embed-text-v1.5'}
11thenlper/gte-large1024Large general text embeddings model1.34{'hf': 'qdrant/gte-large-onnx'}
12mixedbread-ai/mxbai-embed-large-v11024base sentence embedding model1.34{'hf': 'mixedbread-ai/mxbai-embed-large-v1'}
13intfloat/multilingual-e5-large1024Multilingual model, e5-large. Recommend using this model for non-English languages2.24{'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-multilingual-e5-large.tar.gz', 'hf': 'qdrant/multilingual-e5-large-onnx'}
14sentence-transformers/paraphrase-multilingual-mpnet-base-v2768Sentence-transformers model for tasks like clustering or semantic search1.11{'hf': 'xenova/paraphrase-multilingual-mpnet-base-v2'}
15jinaai/jina-embeddings-v2-base-en768English embedding model supporting 8192 sequence length0.55{'hf': 'xenova/jina-embeddings-v2-base-en'}
16jinaai/jina-embeddings-v2-small-en512English embedding model supporting 8192 sequence length0.13{'hf': 'xenova/jina-embeddings-v2-small-en'}
\n", - "
" - ], - "text/plain": [ - " model dim \\\n", - "0 BAAI/bge-base-en 768 \n", - "1 BAAI/bge-base-en-v1.5 768 \n", - "2 BAAI/bge-large-en-v1.5-quantized 1024 \n", - "3 BAAI/bge-large-en-v1.5 1024 \n", - "4 BAAI/bge-small-en 384 \n", - "5 BAAI/bge-small-en-v1.5 384 \n", - "6 BAAI/bge-small-zh-v1.5 512 \n", - "7 sentence-transformers/all-MiniLM-L6-v2 384 \n", - "8 sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 384 \n", - "9 nomic-ai/nomic-embed-text-v1 768 \n", - "10 nomic-ai/nomic-embed-text-v1.5 768 \n", - "11 thenlper/gte-large 1024 \n", - "12 mixedbread-ai/mxbai-embed-large-v1 1024 \n", - "13 intfloat/multilingual-e5-large 1024 \n", - "14 sentence-transformers/paraphrase-multilingual-mpnet-base-v2 768 \n", - "15 jinaai/jina-embeddings-v2-base-en 768 \n", - "16 jinaai/jina-embeddings-v2-small-en 512 \n", - "\n", - " description \\\n", - "0 Base English model \n", - "1 Base English model, v1.5 \n", - "2 Large English model, v1.5 \n", - "3 Large English model, v1.5 \n", - "4 Fast English model \n", - "5 Fast and Default English model \n", - "6 Fast and recommended Chinese model \n", - "7 Sentence Transformer model, MiniLM-L6-v2 \n", - "8 Sentence Transformer model, paraphrase-multilingual-MiniLM-L12-v2 \n", - "9 8192 context length english model \n", - "10 8192 context length english model \n", - "11 Large general text embeddings model \n", - "12 base sentence embedding model \n", - "13 Multilingual model, e5-large. Recommend using this model for non-English languages \n", - "14 Sentence-transformers model for tasks like clustering or semantic search \n", - "15 English embedding model supporting 8192 sequence length \n", - "16 English embedding model supporting 8192 sequence length \n", - "\n", - " size_in_GB \\\n", - "0 0.50 \n", - "1 0.44 \n", - "2 1.34 \n", - "3 1.34 \n", - "4 0.20 \n", - "5 0.13 \n", - "6 0.10 \n", - "7 0.09 \n", - "8 0.46 \n", - "9 0.54 \n", - "10 0.54 \n", - "11 1.34 \n", - "12 1.34 \n", - "13 2.24 \n", - "14 1.11 \n", - "15 0.55 \n", - "16 0.13 \n", - "\n", - " sources \n", - "0 {'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-bge-base-en.tar.gz'} \n", - "1 {'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-bge-base-en-v1.5.tar.gz', 'hf': 'qdrant/bge-base-en-v1.5-onnx-q'} \n", - "2 {'hf': 'qdrant/bge-large-en-v1.5-onnx-q'} \n", - "3 {'hf': 'qdrant/bge-large-en-v1.5-onnx'} \n", - "4 {'url': 'https://storage.googleapis.com/qdrant-fastembed/BAAI-bge-small-en.tar.gz'} \n", - "5 {'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-bge-small-en-v1.5.tar.gz', 'hf': 'qdrant/bge-small-en-v1.5-onnx-q'} \n", - "6 {'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-bge-small-zh-v1.5.tar.gz'} \n", - "7 {'url': 'https://storage.googleapis.com/qdrant-fastembed/sentence-transformers-all-MiniLM-L6-v2.tar.gz', 'hf': 'qdrant/all-MiniLM-L6-v2-onnx'} \n", - "8 {'hf': 'qdrant/paraphrase-multilingual-MiniLM-L12-v2-onnx-Q'} \n", - "9 {'hf': 'nomic-ai/nomic-embed-text-v1'} \n", - "10 {'hf': 'nomic-ai/nomic-embed-text-v1.5'} \n", - "11 {'hf': 'qdrant/gte-large-onnx'} \n", - "12 {'hf': 'mixedbread-ai/mxbai-embed-large-v1'} \n", - "13 {'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-multilingual-e5-large.tar.gz', 'hf': 'qdrant/multilingual-e5-large-onnx'} \n", - "14 {'hf': 'xenova/paraphrase-multilingual-mpnet-base-v2'} \n", - "15 {'hf': 'xenova/jina-embeddings-v2-base-en'} \n", - "16 {'hf': 'xenova/jina-embeddings-v2-small-en'} " - ] + "text/plain": " model dim \\\n0 BAAI/bge-base-en 768 \n1 BAAI/bge-base-en-v1.5 768 \n2 BAAI/bge-large-en-v1.5-quantized 1024 \n3 BAAI/bge-large-en-v1.5 1024 \n4 BAAI/bge-small-en 384 \n5 BAAI/bge-small-en-v1.5 384 \n6 BAAI/bge-small-en-v1.5-quantized 384 \n7 BAAI/bge-small-zh-v1.5 512 \n8 sentence-transformers/all-MiniLM-L6-v2 384 \n9 sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 384 \n10 nomic-ai/nomic-embed-text-v1 768 \n11 nomic-ai/nomic-embed-text-v1.5 768 \n12 thenlper/gte-large 1024 \n13 mixedbread-ai/mxbai-embed-large-v1 1024 \n14 intfloat/multilingual-e5-large 1024 \n15 sentence-transformers/paraphrase-multilingual-mpnet-base-v2 768 \n16 jinaai/jina-embeddings-v2-base-en 768 \n17 jinaai/jina-embeddings-v2-small-en 512 \n\n description \\\n0 Base English model \n1 Base English model, v1.5 \n2 Large English model, v1.5 \n3 Large English model, v1.5 \n4 Fast English model \n5 Fast and Default English model \n6 Fast English model \n7 Fast and recommended Chinese model \n8 Sentence Transformer model, MiniLM-L6-v2 \n9 Sentence Transformer model, paraphrase-multilingual-MiniLM-L12-v2 \n10 8192 context length english model \n11 8192 context length english model \n12 Large general text embeddings model \n13 MixedBread Base sentence embedding model, does well on MTEB \n14 Multilingual model, e5-large. Recommend using this model for non-English languages \n15 Sentence-transformers model for tasks like clustering or semantic search \n16 English embedding model supporting 8192 sequence length \n17 English embedding model supporting 8192 sequence length \n\n size_in_GB \\\n0 0.42 \n1 0.21 \n2 0.64 \n3 1.20 \n4 0.13 \n5 0.13 \n6 0.06 \n7 0.09 \n8 0.09 \n9 0.22 \n10 0.52 \n11 0.52 \n12 1.20 \n13 0.64 \n14 2.24 \n15 1.00 \n16 0.52 \n17 0.12 \n\n sources \n0 {'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-bge-base-en.tar.gz'} \n1 {'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-bge-base-en-v1.5.tar.gz', 'hf': 'qdrant/bge-base-en-v1.5-onnx-q'} \n2 {'hf': 'qdrant/bge-large-en-v1.5-onnx-q'} \n3 {'hf': 'qdrant/bge-large-en-v1.5-onnx'} \n4 {'url': 'https://storage.googleapis.com/qdrant-fastembed/BAAI-bge-small-en.tar.gz'} \n5 {'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-bge-small-en-v1.5.tar.gz'} \n6 {'hf': 'qdrant/bge-small-en-v1.5-onnx-q'} \n7 {'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-bge-small-zh-v1.5.tar.gz'} \n8 {'url': 'https://storage.googleapis.com/qdrant-fastembed/sentence-transformers-all-MiniLM-L6-v2.tar.gz', 'hf': 'qdrant/all-MiniLM-L6-v2-onnx'} \n9 {'hf': 'qdrant/paraphrase-multilingual-MiniLM-L12-v2-onnx-Q'} \n10 {'hf': 'nomic-ai/nomic-embed-text-v1'} \n11 {'hf': 'nomic-ai/nomic-embed-text-v1.5'} \n12 {'hf': 'qdrant/gte-large-onnx'} \n13 {'hf': 'mixedbread-ai/mxbai-embed-large-v1'} \n14 {'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-multilingual-e5-large.tar.gz', 'hf': 'qdrant/multilingual-e5-large-onnx'} \n15 {'hf': 'xenova/paraphrase-multilingual-mpnet-base-v2'} \n16 {'hf': 'xenova/jina-embeddings-v2-base-en'} \n17 {'hf': 'xenova/jina-embeddings-v2-small-en'} ", + "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
modeldimdescriptionsize_in_GBsources
0BAAI/bge-base-en768Base English model0.42{'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-bge-base-en.tar.gz'}
1BAAI/bge-base-en-v1.5768Base English model, v1.50.21{'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-bge-base-en-v1.5.tar.gz', 'hf': 'qdrant/bge-base-en-v1.5-onnx-q'}
2BAAI/bge-large-en-v1.5-quantized1024Large English model, v1.50.64{'hf': 'qdrant/bge-large-en-v1.5-onnx-q'}
3BAAI/bge-large-en-v1.51024Large English model, v1.51.20{'hf': 'qdrant/bge-large-en-v1.5-onnx'}
4BAAI/bge-small-en384Fast English model0.13{'url': 'https://storage.googleapis.com/qdrant-fastembed/BAAI-bge-small-en.tar.gz'}
5BAAI/bge-small-en-v1.5384Fast and Default English model0.13{'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-bge-small-en-v1.5.tar.gz'}
6BAAI/bge-small-en-v1.5-quantized384Fast English model0.06{'hf': 'qdrant/bge-small-en-v1.5-onnx-q'}
7BAAI/bge-small-zh-v1.5512Fast and recommended Chinese model0.09{'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-bge-small-zh-v1.5.tar.gz'}
8sentence-transformers/all-MiniLM-L6-v2384Sentence Transformer model, MiniLM-L6-v20.09{'url': 'https://storage.googleapis.com/qdrant-fastembed/sentence-transformers-all-MiniLM-L6-v2.tar.gz', 'hf': 'qdrant/all-MiniLM-L6-v2-onnx'}
9sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2384Sentence Transformer model, paraphrase-multilingual-MiniLM-L12-v20.22{'hf': 'qdrant/paraphrase-multilingual-MiniLM-L12-v2-onnx-Q'}
10nomic-ai/nomic-embed-text-v17688192 context length english model0.52{'hf': 'nomic-ai/nomic-embed-text-v1'}
11nomic-ai/nomic-embed-text-v1.57688192 context length english model0.52{'hf': 'nomic-ai/nomic-embed-text-v1.5'}
12thenlper/gte-large1024Large general text embeddings model1.20{'hf': 'qdrant/gte-large-onnx'}
13mixedbread-ai/mxbai-embed-large-v11024MixedBread Base sentence embedding model, does well on MTEB0.64{'hf': 'mixedbread-ai/mxbai-embed-large-v1'}
14intfloat/multilingual-e5-large1024Multilingual model, e5-large. Recommend using this model for non-English languages2.24{'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-multilingual-e5-large.tar.gz', 'hf': 'qdrant/multilingual-e5-large-onnx'}
15sentence-transformers/paraphrase-multilingual-mpnet-base-v2768Sentence-transformers model for tasks like clustering or semantic search1.00{'hf': 'xenova/paraphrase-multilingual-mpnet-base-v2'}
16jinaai/jina-embeddings-v2-base-en768English embedding model supporting 8192 sequence length0.52{'hf': 'xenova/jina-embeddings-v2-base-en'}
17jinaai/jina-embeddings-v2-small-en512English embedding model supporting 8192 sequence length0.12{'hf': 'xenova/jina-embeddings-v2-small-en'}
\n
" }, - "execution_count": 1, + "execution_count": 3, "metadata": {}, "output_type": "execute_result" } @@ -274,6 +42,14 @@ "pd.set_option(\"display.max_colwidth\", None)\n", "pd.DataFrame(TextEmbedding.list_supported_models())" ] + }, + { + "cell_type": "code", + "outputs": [], + "source": [], + "metadata": { + "collapsed": false + } } ], "metadata": { From 985ad20d1021acb6c80592ed3086c7c67be9ad99 Mon Sep 17 00:00:00 2001 From: Nirant Kasliwal Date: Mon, 1 Apr 2024 16:12:05 +0530 Subject: [PATCH 5/5] Consistentcy around quantization in supported_onnx_models --- fastembed/text/onnx_embedding.py | 30 ++++++------------------------ 1 file changed, 6 insertions(+), 24 deletions(-) diff --git a/fastembed/text/onnx_embedding.py b/fastembed/text/onnx_embedding.py index 22c4a6c7..c2c8b71a 100644 --- a/fastembed/text/onnx_embedding.py +++ b/fastembed/text/onnx_embedding.py @@ -27,15 +27,6 @@ "hf": "qdrant/bge-base-en-v1.5-onnx-q", }, }, - { - "model": "BAAI/bge-large-en-v1.5-quantized", - "dim": 1024, - "description": "Large English model, v1.5", - "size_in_GB": 0.64, - "sources": { - "hf": "qdrant/bge-large-en-v1.5-onnx-q", - }, - }, { "model": "BAAI/bge-large-en-v1.5", "dim": 1024, @@ -70,15 +61,6 @@ "dim": 384, "description": "Fast and Default English model", "size_in_GB": 0.13, - "sources": { - "url": "https://storage.googleapis.com/qdrant-fastembed/fast-bge-small-en-v1.5.tar.gz", - }, - }, - { - "model": "BAAI/bge-small-en-v1.5-quantized", - "dim": 384, - "description": "Fast English model", - "size_in_GB": 0.06, "sources": { "hf": "qdrant/bge-small-en-v1.5-onnx-q", }, @@ -152,12 +134,12 @@ # ] # } { - "model": "mixedbread-ai/mxbai-embed-large-v1", - "dim": 1024, - "description": "MixedBread Base sentence embedding model, does well on MTEB", - "size_in_GB": 0.64, - "sources": { - "hf": "mixedbread-ai/mxbai-embed-large-v1", + "model": "mixedbread-ai/mxbai-embed-large-v1", + "dim": 1024, + "description": "MixedBread Base sentence embedding model, does well on MTEB", + "size_in_GB": 0.64, + "sources": { + "hf": "mixedbread-ai/mxbai-embed-large-v1", }, }, ]