Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat: Added gte-large, nomic-text 1.5, cleanup #130

Merged
merged 1 commit into from
Feb 21, 2024
Merged

feat: Added gte-large, nomic-text 1.5, cleanup #130

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
94 changes: 59 additions & 35 deletions docs/examples/Supported_Models.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": 6,
"metadata": {},
"outputs": [
{
Expand Down Expand Up @@ -110,46 +110,62 @@
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2</td>\n",
" <td>384</td>\n",
" <td>Sentence Transformer model, paraphrase-multilingual-MiniLM-L12-v2</td>\n",
" <td>0.46</td>\n",
" <td>{'hf': 'qdrant/paraphrase-multilingual-MiniLM-L12-v2-onnx-Q'}</td>\n",
" <td>nomic-ai/nomic-embed-text-v1</td>\n",
" <td>768</td>\n",
" <td>8192 context length english model</td>\n",
" <td>0.54</td>\n",
" <td>{'hf': 'nomic-ai/nomic-embed-text-v1'}</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>nomic-ai/nomic-embed-text-v1</td>\n",
" <td>nomic-ai/nomic-embed-text-v1.5</td>\n",
" <td>768</td>\n",
" <td>8192 context length english model</td>\n",
" <td>0.54</td>\n",
" <td>{'hf': 'nomic-ai/nomic-embed-text-v1'}</td>\n",
" <td>{'hf': 'nomic-ai/nomic-embed-text-v1.5'}</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>thenlper/gte-large</td>\n",
" <td>1024</td>\n",
" <td>Large general text embeddings model</td>\n",
" <td>1.34</td>\n",
" <td>{'hf': 'qdrant/gte-large-onnx'}</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>intfloat/multilingual-e5-large</td>\n",
" <td>1024</td>\n",
" <td>Multilingual model, e5-large. Recommend using this model for non-English languages</td>\n",
" <td>2.24</td>\n",
" <td>{'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-multilingual-e5-large.tar.gz', 'hf': 'qdrant/multilingual-e5-large-onnx'}</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <th>12</th>\n",
" <td>sentence-transformers/paraphrase-multilingual-mpnet-base-v2</td>\n",
" <td>768</td>\n",
" <td>Sentence-transformers model for tasks like clustering or semantic search</td>\n",
" <td>1.11</td>\n",
" <td>{'hf': 'xenova/paraphrase-multilingual-mpnet-base-v2'}</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <th>13</th>\n",
" <td>sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2</td>\n",
" <td>384</td>\n",
" <td>Sentence Transformer model, paraphrase-multilingual-MiniLM-L12-v2</td>\n",
" <td>0.46</td>\n",
" <td>{'hf': 'qdrant/paraphrase-multilingual-MiniLM-L12-v2-onnx-Q'}</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>jinaai/jina-embeddings-v2-base-en</td>\n",
" <td>768</td>\n",
" <td>English embedding model supporting 8192 sequence length</td>\n",
" <td>0.55</td>\n",
" <td>{'hf': 'xenova/jina-embeddings-v2-base-en'}</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <th>15</th>\n",
" <td>jinaai/jina-embeddings-v2-small-en</td>\n",
" <td>512</td>\n",
" <td>English embedding model supporting 8192 sequence length</td>\n",
Expand All @@ -170,12 +186,14 @@
"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 intfloat/multilingual-e5-large 1024 \n",
"11 sentence-transformers/paraphrase-multilingual-mpnet-base-v2 768 \n",
"12 jinaai/jina-embeddings-v2-base-en 768 \n",
"13 jinaai/jina-embeddings-v2-small-en 512 \n",
"8 nomic-ai/nomic-embed-text-v1 768 \n",
"9 nomic-ai/nomic-embed-text-v1.5 768 \n",
"10 thenlper/gte-large 1024 \n",
"11 intfloat/multilingual-e5-large 1024 \n",
"12 sentence-transformers/paraphrase-multilingual-mpnet-base-v2 768 \n",
"13 sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 384 \n",
"14 jinaai/jina-embeddings-v2-base-en 768 \n",
"15 jinaai/jina-embeddings-v2-small-en 512 \n",
"\n",
" description \\\n",
"0 Base English model \n",
Expand All @@ -186,12 +204,14 @@
"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",
"8 8192 context length english model \n",
"9 8192 context length english model \n",
"10 Multilingual model, e5-large. Recommend using this model for non-English languages \n",
"11 Sentence-transformers model for tasks like clustering or semantic search \n",
"12 English embedding model supporting 8192 sequence length \n",
"13 English embedding model supporting 8192 sequence length \n",
"10 Large general text embeddings model \n",
"11 Multilingual model, e5-large. Recommend using this model for non-English languages \n",
"12 Sentence-transformers model for tasks like clustering or semantic search \n",
"13 Sentence Transformer model, paraphrase-multilingual-MiniLM-L12-v2 \n",
"14 English embedding model supporting 8192 sequence length \n",
"15 English embedding model supporting 8192 sequence length \n",
"\n",
" size_in_GB \\\n",
"0 0.50 \n",
Expand All @@ -202,12 +222,14 @@
"5 0.13 \n",
"6 0.10 \n",
"7 0.09 \n",
"8 0.46 \n",
"8 0.54 \n",
"9 0.54 \n",
"10 2.24 \n",
"11 1.11 \n",
"12 0.55 \n",
"13 0.13 \n",
"10 1.34 \n",
"11 2.24 \n",
"12 1.11 \n",
"13 0.46 \n",
"14 0.55 \n",
"15 0.13 \n",
"\n",
" sources \n",
"0 {'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-bge-base-en.tar.gz'} \n",
Expand All @@ -218,15 +240,17 @@
"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 {'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-multilingual-e5-large.tar.gz', 'hf': 'qdrant/multilingual-e5-large-onnx'} \n",
"11 {'hf': 'xenova/paraphrase-multilingual-mpnet-base-v2'} \n",
"12 {'hf': 'xenova/jina-embeddings-v2-base-en'} \n",
"13 {'hf': 'xenova/jina-embeddings-v2-small-en'} "
"8 {'hf': 'nomic-ai/nomic-embed-text-v1'} \n",
"9 {'hf': 'nomic-ai/nomic-embed-text-v1.5'} \n",
"10 {'hf': 'qdrant/gte-large-onnx'} \n",
"11 {'url': 'https://storage.googleapis.com/qdrant-fastembed/fast-multilingual-e5-large.tar.gz', 'hf': 'qdrant/multilingual-e5-large-onnx'} \n",
"12 {'hf': 'xenova/paraphrase-multilingual-mpnet-base-v2'} \n",
"13 {'hf': 'qdrant/paraphrase-multilingual-MiniLM-L12-v2-onnx-Q'} \n",
"14 {'hf': 'xenova/jina-embeddings-v2-base-en'} \n",
"15 {'hf': 'xenova/jina-embeddings-v2-small-en'} "
]
},
"execution_count": 2,
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
Expand Down Expand Up @@ -256,7 +280,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.4"
"version": "3.10.13"
},
"orig_nbformat": 4
},
Expand Down
143 changes: 0 additions & 143 deletions fastembed/models.json
View file
Open in desktop

This file was deleted.

18 changes: 18 additions & 0 deletions fastembed/text/onnx_embedding.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -116,6 +116,24 @@
"hf": "nomic-ai/nomic-embed-text-v1",
},
},
{
"model": "nomic-ai/nomic-embed-text-v1.5",
"dim": 768,
"description": "8192 context length english model",
"size_in_GB": 0.54,
"sources": {
"hf": "nomic-ai/nomic-embed-text-v1.5",
},
},
{
"model": "thenlper/gte-large",
"dim": 1024,
"description": "Large general text embeddings model",
"size_in_GB": 1.34,
"sources": {
"hf": "qdrant/gte-large-onnx",
},
},
# {
# "model": "sentence-transformers/all-MiniLM-L6-v2",
# "dim": 384,
Expand Down
Loading
Loading