Skip to content

Commit

Permalink
feat: Snowflake models (#207)
Browse files Browse the repository at this point in the history 
* feat: Snowflake models

* Added snowflake/snowflake-arctic-embed-m

* docs: snowflake/snowflake-arctic-embed-m
  • Loading branch information
@Anush008
Anush008 authored Apr 19, 2024
1 parent 864217a commit cc4112d
Show file tree
Hide file tree
Showing 3 changed files with 141 additions and 44 deletions.
133 changes: 89 additions & 44 deletions docs/examples/Supported_Models.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -35,7 +35,7 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 2,
"metadata": {},
"outputs": [
{
Expand Down Expand Up @@ -89,90 +89,125 @@
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>snowflake/snowflake-arctic-embed-xs</td>\n",
" <td>384</td>\n",
" <td>Based on all-MiniLM-L6-v2 model with only 22m ...</td>\n",
" <td>0.090</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>jinaai/jina-embeddings-v2-small-en</td>\n",
" <td>512</td>\n",
" <td>English embedding model supporting 8192 sequen...</td>\n",
" <td>0.120</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <th>5</th>\n",
" <td>snowflake/snowflake-arctic-embed-s</td>\n",
" <td>384</td>\n",
" <td>Based on infloat/e5-small-unsupervised, does n...</td>\n",
" <td>0.130</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>BAAI/bge-small-en</td>\n",
" <td>384</td>\n",
" <td>Fast English model</td>\n",
" <td>0.130</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <th>7</th>\n",
" <td>BAAI/bge-base-en-v1.5</td>\n",
" <td>768</td>\n",
" <td>Base English model, v1.5</td>\n",
" <td>0.210</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <th>8</th>\n",
" <td>sentence-transformers/paraphrase-multilingual-...</td>\n",
" <td>384</td>\n",
" <td>Sentence Transformer model, paraphrase-multili...</td>\n",
" <td>0.220</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <th>9</th>\n",
" <td>BAAI/bge-base-en</td>\n",
" <td>768</td>\n",
" <td>Base English model</td>\n",
" <td>0.420</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <th>10</th>\n",
" <td>snowflake/snowflake-arctic-embed-m</td>\n",
" <td>768</td>\n",
" <td>Based on intfloat/e5-base-unsupervised model, ...</td>\n",
" <td>0.430</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>jinaai/jina-embeddings-v2-base-en</td>\n",
" <td>768</td>\n",
" <td>English embedding model supporting 8192 sequen...</td>\n",
" <td>0.520</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>nomic-ai/nomic-embed-text-v1</td>\n",
" <td>768</td>\n",
" <td>8192 context length english model</td>\n",
" <td>0.520</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <th>13</th>\n",
" <td>nomic-ai/nomic-embed-text-v1.5</td>\n",
" <td>768</td>\n",
" <td>8192 context length english model</td>\n",
" <td>0.520</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>jinaai/jina-embeddings-v2-base-en</td>\n",
" <th>14</th>\n",
" <td>snowflake/snowflake-arctic-embed-m-long</td>\n",
" <td>768</td>\n",
" <td>English embedding model supporting 8192 sequen...</td>\n",
" <td>0.520</td>\n",
" <td>Based on nomic-ai/nomic-embed-text-v1-unsuperv...</td>\n",
" <td>0.540</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <th>15</th>\n",
" <td>mixedbread-ai/mxbai-embed-large-v1</td>\n",
" <td>1024</td>\n",
" <td>MixedBread Base sentence embedding model, does...</td>\n",
" <td>0.640</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <th>16</th>\n",
" <td>sentence-transformers/paraphrase-multilingual-...</td>\n",
" <td>768</td>\n",
" <td>Sentence-transformers model for tasks like clu...</td>\n",
" <td>1.000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <th>17</th>\n",
" <td>snowflake/snowflake-arctic-embed-l</td>\n",
" <td>1024</td>\n",
" <td>Based on intfloat/e5-large-unsupervised, large...</td>\n",
" <td>1.020</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>BAAI/bge-large-en-v1.5</td>\n",
" <td>1024</td>\n",
" <td>Large English model, v1.5</td>\n",
" <td>1.200</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <th>19</th>\n",
" <td>thenlper/gte-large</td>\n",
" <td>1024</td>\n",
" <td>Large general text embeddings model</td>\n",
" <td>1.200</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <th>20</th>\n",
" <td>intfloat/multilingual-e5-large</td>\n",
" <td>1024</td>\n",
" <td>Multilingual model, e5-large. Recommend using ...</td>\n",
Expand All @@ -187,40 +222,50 @@
"0 BAAI/bge-small-en-v1.5 384 \n",
"1 BAAI/bge-small-zh-v1.5 512 \n",
"2 sentence-transformers/all-MiniLM-L6-v2 384 \n",
"3 jinaai/jina-embeddings-v2-small-en 512 \n",
"4 BAAI/bge-small-en 384 \n",
"5 BAAI/bge-base-en-v1.5 768 \n",
"6 sentence-transformers/paraphrase-multilingual-... 384 \n",
"7 BAAI/bge-base-en 768 \n",
"8 nomic-ai/nomic-embed-text-v1 768 \n",
"9 nomic-ai/nomic-embed-text-v1.5 768 \n",
"10 jinaai/jina-embeddings-v2-base-en 768 \n",
"11 mixedbread-ai/mxbai-embed-large-v1 1024 \n",
"12 sentence-transformers/paraphrase-multilingual-... 768 \n",
"13 BAAI/bge-large-en-v1.5 1024 \n",
"14 thenlper/gte-large 1024 \n",
"15 intfloat/multilingual-e5-large 1024 \n",
"3 snowflake/snowflake-arctic-embed-xs 384 \n",
"4 jinaai/jina-embeddings-v2-small-en 512 \n",
"5 snowflake/snowflake-arctic-embed-s 384 \n",
"6 BAAI/bge-small-en 384 \n",
"7 BAAI/bge-base-en-v1.5 768 \n",
"8 sentence-transformers/paraphrase-multilingual-... 384 \n",
"9 BAAI/bge-base-en 768 \n",
"10 snowflake/snowflake-arctic-embed-m 768 \n",
"11 jinaai/jina-embeddings-v2-base-en 768 \n",
"12 nomic-ai/nomic-embed-text-v1 768 \n",
"13 nomic-ai/nomic-embed-text-v1.5 768 \n",
"14 snowflake/snowflake-arctic-embed-m-long 768 \n",
"15 mixedbread-ai/mxbai-embed-large-v1 1024 \n",
"16 sentence-transformers/paraphrase-multilingual-... 768 \n",
"17 snowflake/snowflake-arctic-embed-l 1024 \n",
"18 BAAI/bge-large-en-v1.5 1024 \n",
"19 thenlper/gte-large 1024 \n",
"20 intfloat/multilingual-e5-large 1024 \n",
"\n",
" description size_in_GB \n",
"0 Fast and Default English model 0.067 \n",
"1 Fast and recommended Chinese model 0.090 \n",
"2 Sentence Transformer model, MiniLM-L6-v2 0.090 \n",
"3 English embedding model supporting 8192 sequen... 0.120 \n",
"4 Fast English model 0.130 \n",
"5 Base English model, v1.5 0.210 \n",
"6 Sentence Transformer model, paraphrase-multili... 0.220 \n",
"7 Base English model 0.420 \n",
"8 8192 context length english model 0.520 \n",
"9 8192 context length english model 0.520 \n",
"10 English embedding model supporting 8192 sequen... 0.520 \n",
"11 MixedBread Base sentence embedding model, does... 0.640 \n",
"12 Sentence-transformers model for tasks like clu... 1.000 \n",
"13 Large English model, v1.5 1.200 \n",
"14 Large general text embeddings model 1.200 \n",
"15 Multilingual model, e5-large. Recommend using ... 2.240 "
"3 Based on all-MiniLM-L6-v2 model with only 22m ... 0.090 \n",
"4 English embedding model supporting 8192 sequen... 0.120 \n",
"5 Based on infloat/e5-small-unsupervised, does n... 0.130 \n",
"6 Fast English model 0.130 \n",
"7 Base English model, v1.5 0.210 \n",
"8 Sentence Transformer model, paraphrase-multili... 0.220 \n",
"9 Base English model 0.420 \n",
"10 Based on intfloat/e5-base-unsupervised model, ... 0.430 \n",
"11 English embedding model supporting 8192 sequen... 0.520 \n",
"12 8192 context length english model 0.520 \n",
"13 8192 context length english model 0.520 \n",
"14 Based on nomic-ai/nomic-embed-text-v1-unsuperv... 0.540 \n",
"15 MixedBread Base sentence embedding model, does... 0.640 \n",
"16 Sentence-transformers model for tasks like clu... 1.000 \n",
"17 Based on intfloat/e5-large-unsupervised, large... 1.020 \n",
"18 Large English model, v1.5 1.200 \n",
"19 Large general text embeddings model 1.200 \n",
"20 Multilingual model, e5-large. Recommend using ... 2.240 "
]
},
"execution_count": 6,
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
Expand Down
45 changes: 45 additions & 0 deletions fastembed/text/onnx_embedding.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -142,6 +142,51 @@
"hf": "mixedbread-ai/mxbai-embed-large-v1",
},
},
{
"model": "snowflake/snowflake-arctic-embed-xs",
"dim": 384,
"description": "Based on all-MiniLM-L6-v2 model with only 22m parameters, ideal for latency/TCO budgets.",
"size_in_GB": 0.09,
"sources": {
"hf": "snowflake/snowflake-arctic-embed-xs",
},
},
{
"model": "snowflake/snowflake-arctic-embed-s",
"dim": 384,
"description": "Based on infloat/e5-small-unsupervised, does not trade off retrieval accuracy for its small size.",
"size_in_GB": 0.13,
"sources": {
"hf": "snowflake/snowflake-arctic-embed-s",
},
},
{
"model": "snowflake/snowflake-arctic-embed-m",
"dim": 768,
"description": "Based on intfloat/e5-base-unsupervised model, provides the best retrieval without slowing down inference.",
"size_in_GB": 0.43,
"sources": {
"hf": "Snowflake/snowflake-arctic-embed-m",
},
},
{
"model": "snowflake/snowflake-arctic-embed-m-long",
"dim": 768,
"description": "Based on nomic-ai/nomic-embed-text-v1-unsupervised model, 8192 context-length model",
"size_in_GB": 0.54,
"sources": {
"hf": "snowflake/snowflake-arctic-embed-m-long",
},
},
{
"model": "snowflake/snowflake-arctic-embed-l",
"dim": 1024,
"description": "Based on intfloat/e5-large-unsupervised, large model for most accurate retrieval.",
"size_in_GB": 1.02,
"sources": {
"hf": "snowflake/snowflake-arctic-embed-l",
},
},
]


Expand Down
7 changes: 7 additions & 0 deletions tests/test_text_onnx_embeddings.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,13 @@
),
"thenlper/gte-large": np.array([-0.01920587, 0.00113156, -0.00708992, -0.00632304, -0.04025577]),
"mixedbread-ai/mxbai-embed-large-v1": np.array([0.02295546, 0.03196154, 0.016512, -0.04031524, -0.0219634]),
"snowflake/snowflake-arctic-embed-xs": np.array([0.0092, 0.0619, 0.0196, 0.009, -0.0114]),
"snowflake/snowflake-arctic-embed-s": np.array([-0.0416, -0.0867, 0.0209, 0.0554, -0.0272]),
"snowflake/snowflake-arctic-embed-m": np.array([-0.0329, 0.0364, 0.0481, 0.0016, 0.0328]),
"snowflake/snowflake-arctic-embed-m-long": np.array(
[0.0080, -0.0266, -0.0335, 0.0282, 0.0143]
),
"snowflake/snowflake-arctic-embed-l": np.array([0.0189, -0.0673, 0.0183, 0.0124, 0.0146]),
}


Expand Down

0 comments on commit cc4112d

Please sign in to comment.