Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
Commit
·
fd4838e
1
Parent(s):
21c6649
minor fixes
Browse files- app.py +10 -10
- config.yaml +1 -2
- envs.py +1 -0
- model_meta.yaml +230 -230
app.py
CHANGED
|
@@ -28,13 +28,13 @@ def make_clickable_model(model_name, link=None):
|
|
| 28 |
f'<a target="_blank" style="text-decoration: underline" href="{link}">{model_name.split("/")[-1]}</a>'
|
| 29 |
)
|
| 30 |
|
| 31 |
-
EXTERNAL_MODELS = {k for k,v in MODEL_META["
|
| 32 |
-
EXTERNAL_MODEL_TO_LINK = {k: v["link"] for k,v in MODEL_META["
|
| 33 |
-
EXTERNAL_MODEL_TO_DIM = {k: v["dim"] for k,v in MODEL_META["
|
| 34 |
-
EXTERNAL_MODEL_TO_SEQLEN = {k: v["seq_len"] for k,v in MODEL_META["
|
| 35 |
-
EXTERNAL_MODEL_TO_SIZE = {k: v["size"] for k,v in MODEL_META["
|
| 36 |
-
PROPRIETARY_MODELS = {k for k,v in MODEL_META["
|
| 37 |
-
SENTENCE_TRANSFORMERS_COMPATIBLE_MODELS = {k for k,v in MODEL_META["
|
| 38 |
MODELS_TO_SKIP = MODEL_META["models_to_skip"]
|
| 39 |
|
| 40 |
PROPRIETARY_MODELS = {
|
|
@@ -48,8 +48,8 @@ SENTENCE_TRANSFORMERS_COMPATIBLE_MODELS = {
|
|
| 48 |
}
|
| 49 |
|
| 50 |
TASK_TO_TASK_TYPE = {task_category: [] for task_category in TASKS}
|
| 51 |
-
for
|
| 52 |
-
for task_category, task_list in
|
| 53 |
TASK_TO_TASK_TYPE[task_category].extend(task_list)
|
| 54 |
|
| 55 |
def add_lang(examples):
|
|
@@ -365,7 +365,7 @@ for board, board_config in BOARDS_CONFIG.items():
|
|
| 365 |
"language_long": board_config["language_long"],
|
| 366 |
"description": f"**Overall MTEB {overall_pretty_name}** 🔮{board_icon}",
|
| 367 |
"data": boards_data[board]["data_overall"],
|
| 368 |
-
"refresh": partial(get_mteb_average, board_config["tasks"]),
|
| 369 |
"credits": credits,
|
| 370 |
})
|
| 371 |
for task_category, task_category_list in board_config["tasks"].items():
|
|
|
|
| 28 |
f'<a target="_blank" style="text-decoration: underline" href="{link}">{model_name.split("/")[-1]}</a>'
|
| 29 |
)
|
| 30 |
|
| 31 |
+
EXTERNAL_MODELS = {k for k,v in MODEL_META["model_meta"].items() if v.get("is_external", False)}
|
| 32 |
+
EXTERNAL_MODEL_TO_LINK = {k: v["link"] for k,v in MODEL_META["model_meta"].items() if v.get("link", False)}
|
| 33 |
+
EXTERNAL_MODEL_TO_DIM = {k: v["dim"] for k,v in MODEL_META["model_meta"].items() if v.get("dim", False)}
|
| 34 |
+
EXTERNAL_MODEL_TO_SEQLEN = {k: v["seq_len"] for k,v in MODEL_META["model_meta"].items() if v.get("seq_len", False)}
|
| 35 |
+
EXTERNAL_MODEL_TO_SIZE = {k: v["size"] for k,v in MODEL_META["model_meta"].items() if v.get("size", False)}
|
| 36 |
+
PROPRIETARY_MODELS = {k for k,v in MODEL_META["model_meta"].items() if v.get("is_proprietary", False)}
|
| 37 |
+
SENTENCE_TRANSFORMERS_COMPATIBLE_MODELS = {k for k,v in MODEL_META["model_meta"].items() if v.get("is_sentence_transformers_compatible", False)}
|
| 38 |
MODELS_TO_SKIP = MODEL_META["models_to_skip"]
|
| 39 |
|
| 40 |
PROPRIETARY_MODELS = {
|
|
|
|
| 48 |
}
|
| 49 |
|
| 50 |
TASK_TO_TASK_TYPE = {task_category: [] for task_category in TASKS}
|
| 51 |
+
for board_config in BOARDS_CONFIG.values():
|
| 52 |
+
for task_category, task_list in board_config["tasks"].items():
|
| 53 |
TASK_TO_TASK_TYPE[task_category].extend(task_list)
|
| 54 |
|
| 55 |
def add_lang(examples):
|
|
|
|
| 365 |
"language_long": board_config["language_long"],
|
| 366 |
"description": f"**Overall MTEB {overall_pretty_name}** 🔮{board_icon}",
|
| 367 |
"data": boards_data[board]["data_overall"],
|
| 368 |
+
"refresh": lambda: get_mteb_average(board_config["tasks"])[0],#partial(get_mteb_average, board_config["tasks"]),
|
| 369 |
"credits": credits,
|
| 370 |
})
|
| 371 |
for task_category, task_category_list in board_config["tasks"].items():
|
config.yaml
CHANGED
|
@@ -1,4 +1,3 @@
|
|
| 1 |
-
version: 0.0.1
|
| 2 |
config:
|
| 3 |
REPO_ID: "mteb/leaderboard"
|
| 4 |
RESULTS_REPO: mteb/results
|
|
@@ -111,7 +110,7 @@ boards:
|
|
| 111 |
- SummEval
|
| 112 |
en-x:
|
| 113 |
title: "English-X"
|
| 114 |
-
language_long: "
|
| 115 |
has_overall: false
|
| 116 |
acronym: null
|
| 117 |
icon: null
|
|
|
|
|
|
|
| 1 |
config:
|
| 2 |
REPO_ID: "mteb/leaderboard"
|
| 3 |
RESULTS_REPO: mteb/results
|
|
|
|
| 110 |
- SummEval
|
| 111 |
en-x:
|
| 112 |
title: "English-X"
|
| 113 |
+
language_long: "117 (Pairs of: English & other language)"
|
| 114 |
has_overall: false
|
| 115 |
acronym: null
|
| 116 |
icon: null
|
envs.py
CHANGED
|
@@ -37,6 +37,7 @@ RESULTS_REPO = get_config("RESULTS_REPO", "mteb/results")
|
|
| 37 |
CACHE_PATH=get_config("HF_HOME", ".")
|
| 38 |
os.environ["HF_HOME"] = CACHE_PATH
|
| 39 |
|
|
|
|
| 40 |
if not os.access(CACHE_PATH, os.W_OK):
|
| 41 |
print(f"No write access to HF_HOME: {CACHE_PATH}. Resetting to current directory.")
|
| 42 |
CACHE_PATH = "."
|
|
|
|
| 37 |
CACHE_PATH=get_config("HF_HOME", ".")
|
| 38 |
os.environ["HF_HOME"] = CACHE_PATH
|
| 39 |
|
| 40 |
+
# Check if it is using persistent storage
|
| 41 |
if not os.access(CACHE_PATH, os.W_OK):
|
| 42 |
print(f"No write access to HF_HOME: {CACHE_PATH}. Resetting to current directory.")
|
| 43 |
CACHE_PATH = "."
|
model_meta.yaml
CHANGED
|
@@ -1,1028 +1,1028 @@
|
|
| 1 |
-
|
| 2 |
Baichuan-text-embedding:
|
| 3 |
-
dim: 1024
|
| 4 |
-
is_external: true
|
| 5 |
-
is_proprietary: true
|
| 6 |
-
is_sentence_transformers_compatible: false
|
| 7 |
link: https://platform.baichuan-ai.com/docs/text-Embedding
|
| 8 |
seq_len: 512
|
| 9 |
size: null
|
| 10 |
-
Cohere-embed-english-v3.0:
|
| 11 |
dim: 1024
|
| 12 |
is_external: true
|
| 13 |
is_proprietary: true
|
| 14 |
is_sentence_transformers_compatible: false
|
|
|
|
| 15 |
link: https://huggingface.co/Cohere/Cohere-embed-english-v3.0
|
| 16 |
seq_len: 512
|
| 17 |
size: null
|
| 18 |
-
|
| 19 |
-
dim: 384
|
| 20 |
is_external: true
|
| 21 |
is_proprietary: true
|
| 22 |
is_sentence_transformers_compatible: false
|
|
|
|
| 23 |
link: https://huggingface.co/Cohere/Cohere-embed-multilingual-light-v3.0
|
| 24 |
seq_len: 512
|
| 25 |
size: null
|
| 26 |
-
|
| 27 |
-
dim: 1024
|
| 28 |
is_external: true
|
| 29 |
is_proprietary: true
|
| 30 |
is_sentence_transformers_compatible: false
|
|
|
|
| 31 |
link: https://huggingface.co/Cohere/Cohere-embed-multilingual-v3.0
|
| 32 |
seq_len: 512
|
| 33 |
size: null
|
| 34 |
-
|
| 35 |
-
dim: 768
|
| 36 |
is_external: true
|
| 37 |
-
is_proprietary:
|
| 38 |
-
is_sentence_transformers_compatible:
|
|
|
|
| 39 |
link: https://huggingface.co/vesteinn/DanskBERT
|
| 40 |
seq_len: 514
|
| 41 |
size: 125
|
| 42 |
-
|
| 43 |
-
dim: 1024
|
| 44 |
is_external: true
|
| 45 |
is_proprietary: false
|
| 46 |
-
is_sentence_transformers_compatible:
|
|
|
|
| 47 |
link: https://github.com/facebookresearch/LASER
|
| 48 |
seq_len: N/A
|
| 49 |
size: 43
|
| 50 |
-
|
| 51 |
-
dim: 4096
|
| 52 |
is_external: true
|
| 53 |
is_proprietary: false
|
| 54 |
is_sentence_transformers_compatible: false
|
|
|
|
| 55 |
link: https://huggingface.co/McGill-NLP/LLM2Vec-Llama-2-7b-chat-hf-mntp-supervised
|
| 56 |
seq_len: 4096
|
| 57 |
size: 6607
|
| 58 |
-
LLM2Vec-Llama-unsupervised:
|
| 59 |
dim: 4096
|
| 60 |
is_external: true
|
| 61 |
is_proprietary: false
|
| 62 |
is_sentence_transformers_compatible: false
|
|
|
|
| 63 |
link: https://huggingface.co/McGill-NLP/LLM2Vec-Llama-2-7b-chat-hf-mntp
|
| 64 |
seq_len: 4096
|
| 65 |
size: 6607
|
| 66 |
-
LLM2Vec-Mistral-supervised:
|
| 67 |
dim: 4096
|
| 68 |
is_external: true
|
| 69 |
is_proprietary: false
|
| 70 |
is_sentence_transformers_compatible: false
|
|
|
|
| 71 |
link: https://huggingface.co/McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-supervised
|
| 72 |
seq_len: 32768
|
| 73 |
size: 7111
|
| 74 |
-
LLM2Vec-Mistral-unsupervised:
|
| 75 |
dim: 4096
|
| 76 |
is_external: true
|
| 77 |
is_proprietary: false
|
| 78 |
is_sentence_transformers_compatible: false
|
|
|
|
| 79 |
link: https://huggingface.co/McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp
|
| 80 |
seq_len: 32768
|
| 81 |
size: 7111
|
| 82 |
-
|
| 83 |
-
dim: 2048
|
| 84 |
is_external: true
|
| 85 |
is_proprietary: false
|
| 86 |
is_sentence_transformers_compatible: false
|
|
|
|
| 87 |
link: https://huggingface.co/McGill-NLP/LLM2Vec-Sheared-LLaMA-mntp-supervised
|
| 88 |
seq_len: 4096
|
| 89 |
size: 1280
|
| 90 |
-
LLM2Vec-Sheared-Llama-unsupervised:
|
| 91 |
dim: 2048
|
| 92 |
is_external: true
|
| 93 |
is_proprietary: false
|
| 94 |
is_sentence_transformers_compatible: false
|
|
|
|
| 95 |
link: https://huggingface.co/McGill-NLP/LLM2Vec-Sheared-LLaMA-mntp
|
| 96 |
seq_len: 4096
|
| 97 |
size: 1280
|
| 98 |
-
|
| 99 |
-
dim: 768
|
| 100 |
is_external: true
|
| 101 |
is_proprietary: false
|
| 102 |
-
is_sentence_transformers_compatible:
|
|
|
|
| 103 |
link: https://huggingface.co/sentence-transformers/LaBSE
|
| 104 |
seq_len: 512
|
| 105 |
size: 471
|
|
|
|
|
|
|
|
|
|
|
|
|
| 106 |
OpenSearch-text-hybrid:
|
|
|
|
|
|
|
|
|
|
| 107 |
dim: 1792
|
| 108 |
is_external: true
|
| 109 |
is_proprietary: true
|
| 110 |
is_sentence_transformers_compatible: false
|
| 111 |
-
link: https://help.aliyun.com/zh/open-search/vector-search-edition/hybrid-retrieval
|
| 112 |
-
seq_len: 512
|
| 113 |
-
size: null
|
| 114 |
all-MiniLM-L12-v2:
|
| 115 |
-
dim: 384
|
| 116 |
-
is_external: true
|
| 117 |
-
is_proprietary: false
|
| 118 |
-
is_sentence_transformers_compatible: true
|
| 119 |
link: https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2
|
| 120 |
seq_len: 512
|
| 121 |
size: 33
|
| 122 |
-
all-MiniLM-L6-v2:
|
| 123 |
dim: 384
|
| 124 |
is_external: true
|
| 125 |
is_proprietary: false
|
| 126 |
is_sentence_transformers_compatible: true
|
|
|
|
| 127 |
link: https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2
|
| 128 |
seq_len: 512
|
| 129 |
size: 23
|
| 130 |
-
|
| 131 |
-
dim: 768
|
| 132 |
is_external: true
|
| 133 |
is_proprietary: false
|
| 134 |
is_sentence_transformers_compatible: true
|
|
|
|
| 135 |
link: https://huggingface.co/sentence-transformers/all-mpnet-base-v2
|
| 136 |
seq_len: 514
|
| 137 |
size: 110
|
| 138 |
-
allenai-specter:
|
| 139 |
dim: 768
|
| 140 |
is_external: true
|
| 141 |
is_proprietary: false
|
| 142 |
is_sentence_transformers_compatible: true
|
|
|
|
| 143 |
link: https://huggingface.co/sentence-transformers/allenai-specter
|
| 144 |
seq_len: 512
|
| 145 |
size: 110
|
| 146 |
-
bert-base-10lang-cased:
|
| 147 |
dim: 768
|
| 148 |
is_external: true
|
| 149 |
is_proprietary: false
|
| 150 |
is_sentence_transformers_compatible: true
|
|
|
|
| 151 |
link: https://huggingface.co/Geotrend/bert-base-10lang-cased
|
| 152 |
seq_len: 512
|
| 153 |
size: 138
|
| 154 |
-
bert-base-15lang-cased:
|
| 155 |
dim: 768
|
| 156 |
is_external: true
|
| 157 |
is_proprietary: false
|
| 158 |
is_sentence_transformers_compatible: true
|
|
|
|
| 159 |
link: https://huggingface.co/Geotrend/bert-base-15lang-cased
|
| 160 |
seq_len: 512
|
| 161 |
size: 138
|
| 162 |
-
bert-base-25lang-cased:
|
| 163 |
dim: 768
|
| 164 |
is_external: true
|
| 165 |
is_proprietary: false
|
| 166 |
is_sentence_transformers_compatible: true
|
|
|
|
| 167 |
link: https://huggingface.co/Geotrend/bert-base-25lang-cased
|
| 168 |
seq_len: 512
|
| 169 |
size: 138
|
| 170 |
-
bert-base-multilingual-cased:
|
| 171 |
dim: 768
|
| 172 |
is_external: true
|
| 173 |
is_proprietary: false
|
| 174 |
is_sentence_transformers_compatible: true
|
|
|
|
| 175 |
link: https://huggingface.co/google-bert/bert-base-multilingual-cased
|
| 176 |
seq_len: 512
|
| 177 |
size: 179
|
| 178 |
-
bert-base-multilingual-uncased:
|
| 179 |
dim: 768
|
| 180 |
is_external: true
|
| 181 |
is_proprietary: false
|
| 182 |
is_sentence_transformers_compatible: true
|
|
|
|
| 183 |
link: https://huggingface.co/google-bert/bert-base-multilingual-uncased
|
| 184 |
seq_len: 512
|
| 185 |
size: 168
|
| 186 |
-
bert-base-swedish-cased:
|
| 187 |
dim: 768
|
| 188 |
is_external: true
|
| 189 |
is_proprietary: false
|
| 190 |
is_sentence_transformers_compatible: true
|
|
|
|
| 191 |
link: https://huggingface.co/KB/bert-base-swedish-cased
|
| 192 |
seq_len: 512
|
| 193 |
size: 125
|
| 194 |
-
bert-base-uncased:
|
| 195 |
dim: 768
|
| 196 |
is_external: true
|
| 197 |
is_proprietary: false
|
| 198 |
is_sentence_transformers_compatible: true
|
|
|
|
| 199 |
link: https://huggingface.co/bert-base-uncased
|
| 200 |
seq_len: 512
|
| 201 |
size: 110
|
| 202 |
-
bge-base-zh-v1.5:
|
| 203 |
dim: 768
|
| 204 |
is_external: true
|
| 205 |
is_proprietary: false
|
| 206 |
is_sentence_transformers_compatible: true
|
|
|
|
| 207 |
link: https://huggingface.co/BAAI/bge-base-zh-v1.5
|
| 208 |
seq_len: 512
|
| 209 |
size: 102
|
| 210 |
-
|
| 211 |
-
dim: 1024
|
| 212 |
is_external: true
|
| 213 |
is_proprietary: false
|
| 214 |
-
is_sentence_transformers_compatible:
|
|
|
|
| 215 |
link: https://huggingface.co/BAAI/bge-large-en-v1.5
|
| 216 |
seq_len: 512
|
| 217 |
size: null
|
| 218 |
-
bge-large-zh-noinstruct:
|
| 219 |
dim: 1024
|
| 220 |
is_external: true
|
| 221 |
is_proprietary: false
|
| 222 |
-
is_sentence_transformers_compatible:
|
|
|
|
| 223 |
link: https://huggingface.co/BAAI/bge-large-zh-noinstruct
|
| 224 |
seq_len: 512
|
| 225 |
size: 326
|
| 226 |
-
bge-large-zh-v1.5:
|
| 227 |
dim: 1024
|
| 228 |
is_external: true
|
| 229 |
is_proprietary: false
|
| 230 |
is_sentence_transformers_compatible: true
|
|
|
|
| 231 |
link: https://huggingface.co/BAAI/bge-large-zh-v1.5
|
| 232 |
seq_len: 512
|
| 233 |
size: 326
|
| 234 |
-
|
| 235 |
-
dim: 512
|
| 236 |
is_external: true
|
| 237 |
is_proprietary: false
|
| 238 |
is_sentence_transformers_compatible: true
|
|
|
|
| 239 |
link: https://huggingface.co/BAAI/bge-small-zh-v1.5
|
| 240 |
seq_len: 512
|
| 241 |
size: 24
|
| 242 |
-
camembert-base:
|
| 243 |
dim: 512
|
| 244 |
-
is_external:
|
| 245 |
is_proprietary: false
|
| 246 |
is_sentence_transformers_compatible: true
|
|
|
|
| 247 |
link: https://huggingface.co/almanach/camembert-base
|
| 248 |
seq_len: 512
|
| 249 |
size: 111
|
| 250 |
-
|
| 251 |
-
dim: 768
|
| 252 |
is_external: false
|
| 253 |
is_proprietary: false
|
| 254 |
is_sentence_transformers_compatible: true
|
|
|
|
| 255 |
link: https://huggingface.co/almanach/camembert-large
|
| 256 |
seq_len: 512
|
| 257 |
size: 338
|
| 258 |
-
contriever-base-msmarco:
|
| 259 |
dim: 768
|
| 260 |
-
is_external:
|
| 261 |
is_proprietary: false
|
| 262 |
is_sentence_transformers_compatible: true
|
|
|
|
| 263 |
link: https://huggingface.co/nthakur/contriever-base-msmarco
|
| 264 |
seq_len: 512
|
| 265 |
size: 110
|
| 266 |
-
cross-en-de-roberta-sentence-transformer:
|
| 267 |
dim: 768
|
| 268 |
is_external: true
|
| 269 |
is_proprietary: false
|
| 270 |
is_sentence_transformers_compatible: true
|
|
|
|
| 271 |
link: https://huggingface.co/T-Systems-onsite/cross-en-de-roberta-sentence-transformer
|
| 272 |
seq_len: 514
|
| 273 |
size: 278
|
| 274 |
-
|
| 275 |
-
dim: 1024
|
| 276 |
is_external: true
|
| 277 |
is_proprietary: false
|
| 278 |
is_sentence_transformers_compatible: true
|
|
|
|
| 279 |
link: https://huggingface.co/chcaa/dfm-encoder-large-v1
|
| 280 |
seq_len: 512
|
| 281 |
size: 355
|
| 282 |
-
dfm-sentence-encoder-large-1:
|
| 283 |
dim: 1024
|
| 284 |
is_external: true
|
| 285 |
is_proprietary: false
|
| 286 |
is_sentence_transformers_compatible: true
|
|
|
|
| 287 |
link: https://huggingface.co/chcaa/dfm-encoder-large-v1
|
| 288 |
seq_len: 512
|
| 289 |
size: 355
|
| 290 |
-
|
| 291 |
-
|
| 292 |
-
is_external: false
|
| 293 |
is_proprietary: false
|
| 294 |
is_sentence_transformers_compatible: true
|
|
|
|
| 295 |
link: https://huggingface.co/Geotrend/distilbert-base-25lang-cased
|
| 296 |
seq_len: 512
|
| 297 |
size: 110
|
| 298 |
-
distilbert-base-en-fr-cased:
|
| 299 |
dim: 768
|
| 300 |
is_external: false
|
| 301 |
is_proprietary: false
|
| 302 |
is_sentence_transformers_compatible: true
|
|
|
|
| 303 |
link: https://huggingface.co/Geotrend/distilbert-base-en-fr-cased
|
| 304 |
seq_len: 512
|
| 305 |
size: 110
|
| 306 |
-
distilbert-base-en-fr-es-pt-it-cased:
|
| 307 |
dim: 768
|
| 308 |
is_external: false
|
| 309 |
is_proprietary: false
|
| 310 |
is_sentence_transformers_compatible: true
|
|
|
|
| 311 |
link: https://huggingface.co/Geotrend/distilbert-base-en-fr-es-pt-it-cased
|
| 312 |
seq_len: 512
|
| 313 |
size: 110
|
| 314 |
-
distilbert-base-fr-cased:
|
| 315 |
dim: 768
|
| 316 |
is_external: false
|
| 317 |
is_proprietary: false
|
| 318 |
is_sentence_transformers_compatible: true
|
|
|
|
| 319 |
link: https://huggingface.co/Geotrend/distilbert-base-fr-cased
|
| 320 |
seq_len: 512
|
| 321 |
size: 110
|
| 322 |
-
distilbert-base-uncased:
|
| 323 |
dim: 768
|
| 324 |
is_external: false
|
| 325 |
is_proprietary: false
|
| 326 |
is_sentence_transformers_compatible: true
|
|
|
|
| 327 |
link: https://huggingface.co/distilbert-base-uncased
|
| 328 |
seq_len: 512
|
| 329 |
size: 110
|
| 330 |
-
|
| 331 |
-
|
| 332 |
-
is_external: true
|
| 333 |
is_proprietary: false
|
| 334 |
is_sentence_transformers_compatible: true
|
|
|
|
| 335 |
link: https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v2
|
| 336 |
seq_len: 512
|
| 337 |
size: 135
|
| 338 |
-
|
| 339 |
-
dim: 768
|
| 340 |
is_external: true
|
| 341 |
is_proprietary: false
|
| 342 |
is_sentence_transformers_compatible: true
|
|
|
|
| 343 |
link: https://huggingface.co/intfloat/e5-base
|
| 344 |
seq_len: 512
|
| 345 |
size: 110
|
| 346 |
-
|
| 347 |
-
dim: 1024
|
| 348 |
is_external: true
|
| 349 |
is_proprietary: false
|
| 350 |
is_sentence_transformers_compatible: true
|
|
|
|
| 351 |
link: https://huggingface.co/intfloat/e5-large
|
| 352 |
seq_len: 512
|
| 353 |
size: 335
|
| 354 |
-
|
| 355 |
-
dim: 4096
|
| 356 |
is_external: true
|
| 357 |
is_proprietary: false
|
| 358 |
is_sentence_transformers_compatible: true
|
|
|
|
| 359 |
link: https://huggingface.co/intfloat/e5-mistral-7b-instruct
|
| 360 |
seq_len: 32768
|
| 361 |
size: 7111
|
| 362 |
-
|
| 363 |
-
dim: 384
|
| 364 |
is_external: true
|
| 365 |
is_proprietary: false
|
| 366 |
is_sentence_transformers_compatible: true
|
|
|
|
| 367 |
link: https://huggingface.co/intfloat/e5-small
|
| 368 |
seq_len: 512
|
| 369 |
size: 33
|
| 370 |
-
|
| 371 |
-
dim: 256
|
| 372 |
is_external: true
|
| 373 |
is_proprietary: false
|
| 374 |
is_sentence_transformers_compatible: true
|
|
|
|
| 375 |
link: https://huggingface.co/jonfd/electra-small-nordic
|
| 376 |
seq_len: 512
|
| 377 |
size: 23
|
| 378 |
-
electra-small-swedish-cased-discriminator:
|
| 379 |
dim: 256
|
| 380 |
is_external: true
|
| 381 |
is_proprietary: false
|
| 382 |
is_sentence_transformers_compatible: true
|
|
|
|
| 383 |
link: https://huggingface.co/KBLab/electra-small-swedish-cased-discriminator
|
| 384 |
seq_len: 512
|
| 385 |
size: 16
|
| 386 |
-
|
| 387 |
-
dim: 768
|
| 388 |
is_external: true
|
| 389 |
is_proprietary: false
|
| 390 |
is_sentence_transformers_compatible: true
|
|
|
|
| 391 |
link: https://huggingface.co/flaubert/flaubert_base_cased
|
| 392 |
seq_len: 512
|
| 393 |
size: 138
|
| 394 |
-
flaubert_base_uncased:
|
| 395 |
dim: 768
|
| 396 |
is_external: true
|
| 397 |
is_proprietary: false
|
| 398 |
is_sentence_transformers_compatible: true
|
|
|
|
| 399 |
link: https://huggingface.co/flaubert/flaubert_base_uncased
|
| 400 |
seq_len: 512
|
| 401 |
size: 138
|
| 402 |
-
|
| 403 |
-
dim: 1024
|
| 404 |
is_external: true
|
| 405 |
is_proprietary: false
|
| 406 |
is_sentence_transformers_compatible: true
|
|
|
|
| 407 |
link: https://huggingface.co/flaubert/flaubert_large_cased
|
| 408 |
seq_len: 512
|
| 409 |
size: 372
|
| 410 |
-
|
| 411 |
-
dim: 768
|
| 412 |
is_external: true
|
| 413 |
is_proprietary: false
|
| 414 |
is_sentence_transformers_compatible: true
|
|
|
|
| 415 |
link: https://huggingface.co/deepset/gbert-base
|
| 416 |
seq_len: 512
|
| 417 |
size: 110
|
| 418 |
-
|
| 419 |
-
dim: 1024
|
| 420 |
is_external: true
|
| 421 |
is_proprietary: false
|
| 422 |
is_sentence_transformers_compatible: true
|
|
|
|
| 423 |
link: https://huggingface.co/deepset/gbert-large
|
| 424 |
seq_len: 512
|
| 425 |
size: 337
|
| 426 |
-
|
| 427 |
-
dim: 768
|
| 428 |
is_external: true
|
| 429 |
is_proprietary: false
|
| 430 |
is_sentence_transformers_compatible: true
|
|
|
|
| 431 |
link: https://huggingface.co/deepset/gelectra-base
|
| 432 |
seq_len: 512
|
| 433 |
size: 110
|
| 434 |
-
|
| 435 |
-
dim: 1024
|
| 436 |
is_external: true
|
| 437 |
is_proprietary: false
|
| 438 |
is_sentence_transformers_compatible: true
|
|
|
|
| 439 |
link: https://huggingface.co/deepset/gelectra-large
|
| 440 |
seq_len: 512
|
| 441 |
size: 335
|
| 442 |
-
|
| 443 |
-
dim: 300
|
| 444 |
is_external: true
|
| 445 |
is_proprietary: false
|
| 446 |
is_sentence_transformers_compatible: true
|
|
|
|
| 447 |
link: https://huggingface.co/sentence-transformers/average_word_embeddings_glove.6B.300d
|
| 448 |
seq_len: N/A
|
| 449 |
size: 120
|
|
|
|
|
|
|
|
|
|
|
|
|
| 450 |
google-gecko-256.text-embedding-preview-0409:
|
|
|
|
|
|
|
|
|
|
| 451 |
dim: 256
|
| 452 |
is_external: true
|
| 453 |
is_proprietary: true
|
| 454 |
is_sentence_transformers_compatible: false
|
|
|
|
| 455 |
link: https://cloud.google.com/vertex-ai/generative-ai/docs/embeddings/get-text-embeddings#latest_models
|
| 456 |
seq_len: 2048
|
| 457 |
size: 1200
|
| 458 |
-
google-gecko.text-embedding-preview-0409:
|
| 459 |
dim: 768
|
| 460 |
is_external: true
|
| 461 |
is_proprietary: true
|
| 462 |
is_sentence_transformers_compatible: false
|
| 463 |
-
link: https://cloud.google.com/vertex-ai/generative-ai/docs/embeddings/get-text-embeddings#latest_models
|
| 464 |
-
seq_len: 2048
|
| 465 |
-
size: 1200
|
| 466 |
gottbert-base:
|
| 467 |
-
dim: 768
|
| 468 |
-
is_external: true
|
| 469 |
-
is_proprietary: false
|
| 470 |
-
is_sentence_transformers_compatible: true
|
| 471 |
link: https://huggingface.co/uklfr/gottbert-base
|
| 472 |
seq_len: 512
|
| 473 |
size: 127
|
| 474 |
-
gtr-t5-base:
|
| 475 |
dim: 768
|
| 476 |
is_external: true
|
| 477 |
is_proprietary: false
|
| 478 |
is_sentence_transformers_compatible: true
|
|
|
|
| 479 |
link: https://huggingface.co/sentence-transformers/gtr-t5-base
|
| 480 |
seq_len: 512
|
| 481 |
size: 110
|
| 482 |
-
gtr-t5-large:
|
| 483 |
dim: 768
|
| 484 |
is_external: true
|
| 485 |
is_proprietary: false
|
| 486 |
is_sentence_transformers_compatible: true
|
|
|
|
| 487 |
link: https://huggingface.co/sentence-transformers/gtr-t5-large
|
| 488 |
seq_len: 512
|
| 489 |
size: 168
|
| 490 |
-
gtr-t5-xl:
|
| 491 |
dim: 768
|
| 492 |
is_external: true
|
| 493 |
is_proprietary: false
|
| 494 |
is_sentence_transformers_compatible: true
|
|
|
|
| 495 |
link: https://huggingface.co/sentence-transformers/gtr-t5-xl
|
| 496 |
seq_len: 512
|
| 497 |
size: 1240
|
| 498 |
-
gtr-t5-xxl:
|
| 499 |
dim: 768
|
| 500 |
is_external: true
|
| 501 |
is_proprietary: false
|
| 502 |
is_sentence_transformers_compatible: true
|
|
|
|
| 503 |
link: https://huggingface.co/sentence-transformers/gtr-t5-xxl
|
| 504 |
seq_len: 512
|
| 505 |
size: 4865
|
| 506 |
-
herbert-base-retrieval-v2:
|
| 507 |
dim: 768
|
| 508 |
is_external: true
|
| 509 |
is_proprietary: false
|
| 510 |
is_sentence_transformers_compatible: true
|
|
|
|
| 511 |
link: https://huggingface.co/ipipan/herbert-base-retrieval-v2
|
| 512 |
seq_len: 514
|
| 513 |
size: 125
|
| 514 |
-
|
| 515 |
-
dim: 300
|
| 516 |
is_external: true
|
| 517 |
is_proprietary: false
|
| 518 |
is_sentence_transformers_compatible: true
|
|
|
|
| 519 |
link: https://huggingface.co/sentence-transformers/average_word_embeddings_komninos
|
| 520 |
seq_len: N/A
|
| 521 |
size: 134
|
| 522 |
-
|
| 523 |
-
dim: 768
|
| 524 |
is_external: true
|
| 525 |
is_proprietary: false
|
| 526 |
is_sentence_transformers_compatible: true
|
|
|
|
| 527 |
link: https://huggingface.co/silk-road/luotuo-bert-medium
|
| 528 |
seq_len: 512
|
| 529 |
size: 328
|
| 530 |
-
m3e-base:
|
| 531 |
dim: 768
|
| 532 |
is_external: true
|
| 533 |
is_proprietary: false
|
| 534 |
is_sentence_transformers_compatible: true
|
|
|
|
| 535 |
link: https://huggingface.co/moka-ai/m3e-base
|
| 536 |
seq_len: 512
|
| 537 |
size: 102
|
| 538 |
-
m3e-large:
|
| 539 |
dim: 768
|
| 540 |
is_external: true
|
| 541 |
is_proprietary: false
|
| 542 |
is_sentence_transformers_compatible: true
|
|
|
|
| 543 |
link: https://huggingface.co/moka-ai/m3e-large
|
| 544 |
seq_len: 512
|
| 545 |
size: 102
|
|
|
|
|
|
|
|
|
|
|
|
|
| 546 |
mistral-embed:
|
|
|
|
|
|
|
|
|
|
| 547 |
dim: 1024
|
| 548 |
is_external: true
|
| 549 |
is_proprietary: true
|
| 550 |
is_sentence_transformers_compatible: false
|
| 551 |
-
link: https://docs.mistral.ai/guides/embeddings
|
| 552 |
-
seq_len: null
|
| 553 |
-
size: null
|
| 554 |
msmarco-bert-co-condensor:
|
| 555 |
-
dim: 768
|
| 556 |
-
is_external: true
|
| 557 |
-
is_proprietary: false
|
| 558 |
-
is_sentence_transformers_compatible: true
|
| 559 |
link: https://huggingface.co/sentence-transformers/msmarco-bert-co-condensor
|
| 560 |
seq_len: 512
|
| 561 |
size: 110
|
| 562 |
-
|
| 563 |
-
dim: 384
|
| 564 |
is_external: true
|
| 565 |
is_proprietary: false
|
| 566 |
is_sentence_transformers_compatible: true
|
|
|
|
| 567 |
link: https://huggingface.co/sentence-transformers/multi-qa-MiniLM-L6-cos-v1
|
| 568 |
seq_len: 512
|
| 569 |
size: 23
|
| 570 |
-
|
| 571 |
-
dim: 768
|
| 572 |
is_external: true
|
| 573 |
is_proprietary: false
|
| 574 |
is_sentence_transformers_compatible: true
|
|
|
|
| 575 |
link: https://huggingface.co/intfloat/multilingual-e5-base
|
| 576 |
seq_len: 514
|
| 577 |
size: 278
|
| 578 |
-
|
| 579 |
-
dim: 1024
|
| 580 |
is_external: true
|
| 581 |
is_proprietary: false
|
| 582 |
is_sentence_transformers_compatible: true
|
|
|
|
| 583 |
link: https://huggingface.co/intfloat/multilingual-e5-large
|
| 584 |
seq_len: 514
|
| 585 |
size: 560
|
| 586 |
-
|
| 587 |
-
dim: 384
|
| 588 |
is_external: true
|
| 589 |
is_proprietary: false
|
| 590 |
is_sentence_transformers_compatible: true
|
|
|
|
| 591 |
link: https://huggingface.co/intfloat/multilingual-e5-small
|
| 592 |
seq_len: 512
|
| 593 |
size: 118
|
| 594 |
-
|
| 595 |
-
dim: 768
|
| 596 |
is_external: true
|
| 597 |
is_proprietary: false
|
| 598 |
is_sentence_transformers_compatible: true
|
|
|
|
| 599 |
link: https://huggingface.co/NbAiLab/nb-bert-base
|
| 600 |
seq_len: 512
|
| 601 |
size: 179
|
| 602 |
-
|
| 603 |
-
dim: 1024
|
| 604 |
is_external: true
|
| 605 |
is_proprietary: false
|
| 606 |
is_sentence_transformers_compatible: true
|
|
|
|
| 607 |
link: https://huggingface.co/NbAiLab/nb-bert-large
|
| 608 |
seq_len: 512
|
| 609 |
size: 355
|
| 610 |
-
|
| 611 |
-
dim: 128
|
| 612 |
is_external: true
|
| 613 |
is_proprietary: false
|
| 614 |
is_sentence_transformers_compatible: true
|
|
|
|
| 615 |
link: https://huggingface.co/nomic-ai/nomic-embed-text-v1.5
|
| 616 |
seq_len: 8192
|
| 617 |
size: 138
|
| 618 |
-
|
| 619 |
-
dim: 256
|
| 620 |
is_external: true
|
| 621 |
is_proprietary: false
|
| 622 |
is_sentence_transformers_compatible: true
|
|
|
|
| 623 |
link: https://huggingface.co/nomic-ai/nomic-embed-text-v1.5
|
| 624 |
seq_len: 8192
|
| 625 |
size: 138
|
| 626 |
-
|
| 627 |
-
dim: 512
|
| 628 |
is_external: true
|
| 629 |
is_proprietary: false
|
| 630 |
is_sentence_transformers_compatible: true
|
|
|
|
| 631 |
link: https://huggingface.co/nomic-ai/nomic-embed-text-v1.5
|
| 632 |
seq_len: 8192
|
| 633 |
size: 138
|
| 634 |
-
|
| 635 |
-
dim: 64
|
| 636 |
is_external: true
|
| 637 |
is_proprietary: false
|
| 638 |
is_sentence_transformers_compatible: true
|
|
|
|
| 639 |
link: https://huggingface.co/nomic-ai/nomic-embed-text-v1.5
|
| 640 |
seq_len: 8192
|
| 641 |
size: 138
|
| 642 |
-
|
| 643 |
-
dim: 768
|
| 644 |
is_external: true
|
| 645 |
is_proprietary: false
|
| 646 |
is_sentence_transformers_compatible: true
|
|
|
|
| 647 |
link: https://huggingface.co/ltg/norbert3-base
|
| 648 |
seq_len: 512
|
| 649 |
size: 131
|
| 650 |
-
|
| 651 |
-
dim: 1024
|
| 652 |
is_external: true
|
| 653 |
is_proprietary: false
|
| 654 |
is_sentence_transformers_compatible: true
|
|
|
|
| 655 |
link: https://huggingface.co/ltg/norbert3-large
|
| 656 |
seq_len: 512
|
| 657 |
size: 368
|
| 658 |
-
|
| 659 |
-
dim: 384
|
| 660 |
is_external: true
|
| 661 |
is_proprietary: false
|
| 662 |
is_sentence_transformers_compatible: true
|
|
|
|
| 663 |
link: https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
|
| 664 |
seq_len: 512
|
| 665 |
size: 118
|
| 666 |
-
|
| 667 |
-
dim: 768
|
| 668 |
is_external: true
|
| 669 |
is_proprietary: false
|
| 670 |
is_sentence_transformers_compatible: true
|
|
|
|
| 671 |
link: https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2
|
| 672 |
seq_len: 514
|
| 673 |
size: 278
|
| 674 |
-
sentence-bert-swedish-cased:
|
| 675 |
dim: 768
|
| 676 |
is_external: true
|
| 677 |
is_proprietary: false
|
| 678 |
is_sentence_transformers_compatible: true
|
|
|
|
| 679 |
link: https://huggingface.co/KBLab/sentence-bert-swedish-cased
|
| 680 |
seq_len: 512
|
| 681 |
size: 125
|
| 682 |
-
sentence-camembert-base:
|
| 683 |
dim: 768
|
| 684 |
is_external: true
|
| 685 |
is_proprietary: false
|
| 686 |
is_sentence_transformers_compatible: true
|
|
|
|
| 687 |
link: https://huggingface.co/dangvantuan/sentence-camembert-base
|
| 688 |
seq_len: 512
|
| 689 |
size: 110
|
| 690 |
-
|
| 691 |
-
dim: 1024
|
| 692 |
is_external: true
|
| 693 |
is_proprietary: false
|
| 694 |
is_sentence_transformers_compatible: true
|
|
|
|
| 695 |
link: https://huggingface.co/dangvantuan/sentence-camembert-large
|
| 696 |
seq_len: 512
|
| 697 |
size: 337
|
| 698 |
-
|
| 699 |
-
dim: 2048
|
| 700 |
is_external: true
|
| 701 |
is_proprietary: false
|
| 702 |
is_sentence_transformers_compatible: true
|
|
|
|
| 703 |
link: https://huggingface.co/Wissam42/sentence-croissant-llm-base
|
| 704 |
seq_len: 2048
|
| 705 |
size: 1280
|
| 706 |
-
|
| 707 |
-
dim: 768
|
| 708 |
is_external: true
|
| 709 |
is_proprietary: false
|
| 710 |
is_sentence_transformers_compatible: true
|
|
|
|
| 711 |
link: https://huggingface.co/sentence-transformers/sentence-t5-base
|
| 712 |
seq_len: 512
|
| 713 |
size: 110
|
| 714 |
-
sentence-t5-large:
|
| 715 |
dim: 768
|
| 716 |
is_external: true
|
| 717 |
is_proprietary: false
|
| 718 |
is_sentence_transformers_compatible: true
|
|
|
|
| 719 |
link: https://huggingface.co/sentence-transformers/sentence-t5-large
|
| 720 |
seq_len: 512
|
| 721 |
size: 168
|
| 722 |
-
sentence-t5-xl:
|
| 723 |
dim: 768
|
| 724 |
is_external: true
|
| 725 |
is_proprietary: false
|
| 726 |
is_sentence_transformers_compatible: true
|
|
|
|
| 727 |
link: https://huggingface.co/sentence-transformers/sentence-t5-xl
|
| 728 |
seq_len: 512
|
| 729 |
size: 1240
|
| 730 |
-
sentence-t5-xxl:
|
| 731 |
dim: 768
|
| 732 |
is_external: true
|
| 733 |
is_proprietary: false
|
| 734 |
is_sentence_transformers_compatible: true
|
|
|
|
| 735 |
link: https://huggingface.co/sentence-transformers/sentence-t5-xxl
|
| 736 |
seq_len: 512
|
| 737 |
size: 4865
|
| 738 |
-
silver-retriever-base-v1:
|
| 739 |
dim: 768
|
| 740 |
is_external: true
|
| 741 |
is_proprietary: false
|
| 742 |
is_sentence_transformers_compatible: true
|
|
|
|
| 743 |
link: https://huggingface.co/ipipan/silver-retriever-base-v1
|
| 744 |
seq_len: 514
|
| 745 |
size: 125
|
| 746 |
-
st-polish-paraphrase-from-distilroberta:
|
| 747 |
dim: 768
|
| 748 |
is_external: true
|
| 749 |
is_proprietary: false
|
| 750 |
is_sentence_transformers_compatible: true
|
|
|
|
| 751 |
link: https://huggingface.co/sdadas/st-polish-paraphrase-from-distilroberta
|
| 752 |
seq_len: 514
|
| 753 |
size: 125
|
| 754 |
-
st-polish-paraphrase-from-mpnet:
|
| 755 |
dim: 768
|
| 756 |
is_external: true
|
| 757 |
is_proprietary: false
|
| 758 |
is_sentence_transformers_compatible: true
|
|
|
|
| 759 |
link: https://huggingface.co/sdadas/st-polish-paraphrase-from-mpnet
|
| 760 |
seq_len: 514
|
| 761 |
size: 125
|
| 762 |
-
sup-simcse-bert-base-uncased:
|
| 763 |
dim: 768
|
| 764 |
is_external: true
|
| 765 |
is_proprietary: false
|
| 766 |
is_sentence_transformers_compatible: true
|
|
|
|
| 767 |
link: https://huggingface.co/princeton-nlp/sup-simcse-bert-base-uncased
|
| 768 |
seq_len: 512
|
| 769 |
size: 110
|
|
|
|
|
|
|
|
|
|
|
|
|
| 770 |
text-embedding-3-large:
|
|
|
|
|
|
|
|
|
|
| 771 |
dim: 3072
|
| 772 |
is_external: true
|
| 773 |
is_proprietary: true
|
| 774 |
is_sentence_transformers_compatible: false
|
|
|
|
| 775 |
link: https://openai.com/blog/new-embedding-models-and-api-updates
|
| 776 |
seq_len: 8191
|
| 777 |
size: null
|
| 778 |
-
text-embedding-3-large-256:
|
| 779 |
dim: 256
|
| 780 |
is_external: true
|
| 781 |
is_proprietary: true
|
| 782 |
is_sentence_transformers_compatible: false
|
|
|
|
| 783 |
link: https://openai.com/blog/new-embedding-models-and-api-updates
|
| 784 |
seq_len: 8191
|
| 785 |
size: null
|
| 786 |
-
text-embedding-3-small:
|
| 787 |
dim: 1536
|
| 788 |
is_external: true
|
| 789 |
is_proprietary: true
|
| 790 |
is_sentence_transformers_compatible: false
|
| 791 |
-
|
|
|
|
| 792 |
seq_len: 8191
|
| 793 |
size: null
|
| 794 |
-
text-embedding-ada-002:
|
| 795 |
dim: 1536
|
| 796 |
is_external: true
|
| 797 |
is_proprietary: true
|
| 798 |
is_sentence_transformers_compatible: false
|
| 799 |
-
link: https://openai.com/blog/new-and-improved-embedding-model
|
| 800 |
-
seq_len: 8191
|
| 801 |
-
size: null
|
| 802 |
text-search-ada-001:
|
|
|
|
|
|
|
|
|
|
| 803 |
dim: 1024
|
| 804 |
is_external: true
|
| 805 |
is_proprietary: true
|
| 806 |
is_sentence_transformers_compatible: false
|
|
|
|
| 807 |
link: https://openai.com/blog/introducing-text-and-code-embeddings
|
| 808 |
seq_len: 2046
|
| 809 |
size: null
|
| 810 |
-
text-search-ada-doc-001:
|
| 811 |
dim: 1024
|
| 812 |
is_external: true
|
| 813 |
is_proprietary: true
|
| 814 |
is_sentence_transformers_compatible: false
|
|
|
|
| 815 |
link: https://openai.com/blog/introducing-text-and-code-embeddings
|
| 816 |
seq_len: 2046
|
| 817 |
size: null
|
| 818 |
-
text-search-ada-query-001:
|
| 819 |
dim: 1024
|
| 820 |
is_external: false
|
| 821 |
is_proprietary: true
|
| 822 |
is_sentence_transformers_compatible: false
|
|
|
|
| 823 |
link: https://openai.com/blog/introducing-text-and-code-embeddings
|
| 824 |
seq_len: 2046
|
| 825 |
size: null
|
| 826 |
-
text-search-babbage-001:
|
| 827 |
dim: 2048
|
| 828 |
is_external: true
|
| 829 |
is_proprietary: true
|
| 830 |
is_sentence_transformers_compatible: false
|
|
|
|
| 831 |
link: https://openai.com/blog/introducing-text-and-code-embeddings
|
| 832 |
seq_len: 2046
|
| 833 |
size: null
|
| 834 |
-
text-search-curie-001:
|
| 835 |
dim: 4096
|
| 836 |
is_external: true
|
| 837 |
is_proprietary: true
|
| 838 |
is_sentence_transformers_compatible: false
|
|
|
|
| 839 |
link: https://openai.com/blog/introducing-text-and-code-embeddings
|
| 840 |
seq_len: 2046
|
| 841 |
size: null
|
| 842 |
-
text-search-davinci-001:
|
| 843 |
dim: 12288
|
| 844 |
is_external: true
|
| 845 |
is_proprietary: true
|
| 846 |
is_sentence_transformers_compatible: false
|
|
|
|
| 847 |
link: https://openai.com/blog/introducing-text-and-code-embeddings
|
| 848 |
seq_len: 2046
|
| 849 |
size: null
|
| 850 |
-
text-similarity-ada-001:
|
| 851 |
dim: 1024
|
| 852 |
is_external: true
|
| 853 |
is_proprietary: true
|
| 854 |
is_sentence_transformers_compatible: false
|
|
|
|
| 855 |
link: https://openai.com/blog/introducing-text-and-code-embeddings
|
| 856 |
seq_len: 2046
|
| 857 |
size: null
|
| 858 |
-
text-similarity-babbage-001:
|
| 859 |
dim: 2048
|
| 860 |
is_external: true
|
| 861 |
is_proprietary: true
|
| 862 |
is_sentence_transformers_compatible: false
|
|
|
|
| 863 |
link: https://openai.com/blog/introducing-text-and-code-embeddings
|
| 864 |
seq_len: 2046
|
| 865 |
size: null
|
| 866 |
-
text-similarity-curie-001:
|
| 867 |
dim: 4096
|
| 868 |
is_external: true
|
| 869 |
is_proprietary: true
|
| 870 |
is_sentence_transformers_compatible: false
|
|
|
|
| 871 |
link: https://openai.com/blog/introducing-text-and-code-embeddings
|
| 872 |
seq_len: 2046
|
| 873 |
size: null
|
| 874 |
-
text-similarity-davinci-001:
|
| 875 |
dim: 12288
|
| 876 |
is_external: true
|
| 877 |
is_proprietary: true
|
| 878 |
is_sentence_transformers_compatible: false
|
| 879 |
-
link: https://openai.com/blog/introducing-text-and-code-embeddings
|
| 880 |
-
seq_len: 2046
|
| 881 |
-
size: null
|
| 882 |
text2vec-base-chinese:
|
|
|
|
|
|
|
|
|
|
| 883 |
dim: 768
|
| 884 |
is_external: true
|
| 885 |
is_proprietary: false
|
| 886 |
is_sentence_transformers_compatible: true
|
| 887 |
-
link: https://huggingface.co/shibing624/text2vec-base-chinese
|
| 888 |
-
seq_len: 512
|
| 889 |
-
size: 102
|
| 890 |
text2vec-base-multilingual:
|
|
|
|
|
|
|
|
|
|
| 891 |
dim: null
|
| 892 |
is_external: true
|
| 893 |
is_proprietary: false
|
| 894 |
is_sentence_transformers_compatible: false
|
| 895 |
-
link: null
|
| 896 |
-
seq_len: null
|
| 897 |
-
size: null
|
| 898 |
text2vec-large-chinese:
|
|
|
|
|
|
|
|
|
|
| 899 |
dim: 1024
|
| 900 |
is_external: true
|
| 901 |
is_proprietary: false
|
| 902 |
is_sentence_transformers_compatible: true
|
| 903 |
-
link: https://huggingface.co/GanymedeNil/text2vec-large-chinese
|
| 904 |
-
seq_len: 512
|
| 905 |
-
size: 326
|
| 906 |
titan-embed-text-v1:
|
| 907 |
-
dim: 1536
|
| 908 |
-
is_external: true
|
| 909 |
-
is_proprietary: true
|
| 910 |
-
is_sentence_transformers_compatible: false
|
| 911 |
link: https://docs.aws.amazon.com/bedrock/latest/userguide/embeddings.html
|
| 912 |
seq_len: 8000
|
| 913 |
size: null
|
| 914 |
-
udever-bloom-1b1:
|
| 915 |
dim: 1536
|
| 916 |
is_external: true
|
| 917 |
-
is_proprietary:
|
| 918 |
-
is_sentence_transformers_compatible:
|
|
|
|
| 919 |
link: https://huggingface.co/izhx/udever-bloom-1b1
|
| 920 |
seq_len: 2048
|
| 921 |
size: null
|
| 922 |
-
|
| 923 |
-
dim: 1024
|
| 924 |
is_external: true
|
| 925 |
is_proprietary: false
|
| 926 |
is_sentence_transformers_compatible: true
|
|
|
|
| 927 |
link: https://huggingface.co/izhx/udever-bloom-560m
|
| 928 |
seq_len: 2048
|
| 929 |
size: null
|
| 930 |
-
|
| 931 |
-
dim: 512
|
| 932 |
is_external: true
|
| 933 |
is_proprietary: false
|
| 934 |
is_sentence_transformers_compatible: true
|
|
|
|
| 935 |
link: https://huggingface.co/vprelovac/universal-sentence-encoder-multilingual-3
|
| 936 |
seq_len: 512
|
| 937 |
size: null
|
| 938 |
-
universal-sentence-encoder-multilingual-large-3:
|
| 939 |
dim: 512
|
| 940 |
is_external: true
|
| 941 |
is_proprietary: false
|
| 942 |
is_sentence_transformers_compatible: true
|
|
|
|
| 943 |
link: https://huggingface.co/vprelovac/universal-sentence-encoder-multilingual-large-3
|
| 944 |
seq_len: 512
|
| 945 |
size: null
|
| 946 |
-
|
| 947 |
-
dim: 768
|
| 948 |
is_external: true
|
| 949 |
is_proprietary: false
|
| 950 |
is_sentence_transformers_compatible: true
|
|
|
|
| 951 |
link: https://huggingface.co/princeton-nlp/unsup-simcse-bert-base-uncased
|
| 952 |
seq_len: 512
|
| 953 |
size: 110
|
| 954 |
-
use-cmlm-multilingual:
|
| 955 |
dim: 768
|
| 956 |
is_external: true
|
| 957 |
is_proprietary: false
|
| 958 |
is_sentence_transformers_compatible: true
|
|
|
|
| 959 |
link: https://huggingface.co/sentence-transformers/use-cmlm-multilingual
|
| 960 |
seq_len: 512
|
| 961 |
size: 472
|
|
|
|
|
|
|
|
|
|
|
|
|
| 962 |
voyage-2:
|
|
|
|
|
|
|
|
|
|
| 963 |
dim: 1024
|
| 964 |
is_external: true
|
| 965 |
is_proprietary: true
|
| 966 |
is_sentence_transformers_compatible: false
|
|
|
|
| 967 |
link: https://docs.voyageai.com/embeddings/
|
| 968 |
-
seq_len:
|
| 969 |
size: null
|
| 970 |
-
voyage-code-2:
|
| 971 |
dim: 1536
|
| 972 |
is_external: true
|
| 973 |
is_proprietary: true
|
| 974 |
is_sentence_transformers_compatible: false
|
|
|
|
| 975 |
link: https://docs.voyageai.com/embeddings/
|
| 976 |
seq_len: 16000
|
| 977 |
size: null
|
| 978 |
-
voyage-large-2-instruct:
|
| 979 |
dim: 1024
|
| 980 |
is_external: true
|
| 981 |
is_proprietary: false
|
| 982 |
is_sentence_transformers_compatible: false
|
|
|
|
| 983 |
link: https://docs.voyageai.com/embeddings/
|
| 984 |
-
seq_len:
|
| 985 |
size: null
|
| 986 |
-
voyage-law-2:
|
| 987 |
dim: 1024
|
| 988 |
is_external: true
|
| 989 |
is_proprietary: true
|
| 990 |
is_sentence_transformers_compatible: false
|
|
|
|
| 991 |
link: https://docs.voyageai.com/embeddings/
|
| 992 |
seq_len: 4000
|
| 993 |
size: null
|
| 994 |
-
voyage-lite-01-instruct:
|
| 995 |
dim: 1024
|
| 996 |
is_external: true
|
| 997 |
is_proprietary: true
|
| 998 |
is_sentence_transformers_compatible: false
|
|
|
|
| 999 |
link: https://docs.voyageai.com/embeddings/
|
| 1000 |
seq_len: 4000
|
| 1001 |
-
size:
|
| 1002 |
-
voyage-lite-02-instruct:
|
| 1003 |
dim: 1024
|
| 1004 |
is_external: true
|
| 1005 |
is_proprietary: true
|
| 1006 |
is_sentence_transformers_compatible: false
|
| 1007 |
-
link: https://docs.voyageai.com/embeddings/
|
| 1008 |
-
seq_len: 4000
|
| 1009 |
-
size: 1220
|
| 1010 |
xlm-roberta-base:
|
| 1011 |
-
dim: 768
|
| 1012 |
-
is_external: true
|
| 1013 |
-
is_proprietary: false
|
| 1014 |
-
is_sentence_transformers_compatible: true
|
| 1015 |
link: https://huggingface.co/xlm-roberta-base
|
| 1016 |
seq_len: 514
|
| 1017 |
size: 279
|
| 1018 |
-
|
| 1019 |
-
dim: 1024
|
| 1020 |
is_external: true
|
| 1021 |
is_proprietary: false
|
| 1022 |
is_sentence_transformers_compatible: true
|
|
|
|
| 1023 |
link: https://huggingface.co/xlm-roberta-large
|
| 1024 |
seq_len: 514
|
| 1025 |
size: 560
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1026 |
models_to_skip:
|
| 1027 |
- michaelfeil/ct2fast-e5-large-v2
|
| 1028 |
- McGill-NLP/LLM2Vec-Sheared-LLaMA-mntp-unsup-simcse
|
|
|
|
| 1 |
+
model_meta:
|
| 2 |
Baichuan-text-embedding:
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
link: https://platform.baichuan-ai.com/docs/text-Embedding
|
| 4 |
seq_len: 512
|
| 5 |
size: null
|
|
|
|
| 6 |
dim: 1024
|
| 7 |
is_external: true
|
| 8 |
is_proprietary: true
|
| 9 |
is_sentence_transformers_compatible: false
|
| 10 |
+
Cohere-embed-english-v3.0:
|
| 11 |
link: https://huggingface.co/Cohere/Cohere-embed-english-v3.0
|
| 12 |
seq_len: 512
|
| 13 |
size: null
|
| 14 |
+
dim: 1024
|
|
|
|
| 15 |
is_external: true
|
| 16 |
is_proprietary: true
|
| 17 |
is_sentence_transformers_compatible: false
|
| 18 |
+
Cohere-embed-multilingual-light-v3.0:
|
| 19 |
link: https://huggingface.co/Cohere/Cohere-embed-multilingual-light-v3.0
|
| 20 |
seq_len: 512
|
| 21 |
size: null
|
| 22 |
+
dim: 384
|
|
|
|
| 23 |
is_external: true
|
| 24 |
is_proprietary: true
|
| 25 |
is_sentence_transformers_compatible: false
|
| 26 |
+
Cohere-embed-multilingual-v3.0:
|
| 27 |
link: https://huggingface.co/Cohere/Cohere-embed-multilingual-v3.0
|
| 28 |
seq_len: 512
|
| 29 |
size: null
|
| 30 |
+
dim: 1024
|
|
|
|
| 31 |
is_external: true
|
| 32 |
+
is_proprietary: true
|
| 33 |
+
is_sentence_transformers_compatible: false
|
| 34 |
+
DanskBERT:
|
| 35 |
link: https://huggingface.co/vesteinn/DanskBERT
|
| 36 |
seq_len: 514
|
| 37 |
size: 125
|
| 38 |
+
dim: 768
|
|
|
|
| 39 |
is_external: true
|
| 40 |
is_proprietary: false
|
| 41 |
+
is_sentence_transformers_compatible: true
|
| 42 |
+
LASER2:
|
| 43 |
link: https://github.com/facebookresearch/LASER
|
| 44 |
seq_len: N/A
|
| 45 |
size: 43
|
| 46 |
+
dim: 1024
|
|
|
|
| 47 |
is_external: true
|
| 48 |
is_proprietary: false
|
| 49 |
is_sentence_transformers_compatible: false
|
| 50 |
+
LLM2Vec-Llama-supervised:
|
| 51 |
link: https://huggingface.co/McGill-NLP/LLM2Vec-Llama-2-7b-chat-hf-mntp-supervised
|
| 52 |
seq_len: 4096
|
| 53 |
size: 6607
|
|
|
|
| 54 |
dim: 4096
|
| 55 |
is_external: true
|
| 56 |
is_proprietary: false
|
| 57 |
is_sentence_transformers_compatible: false
|
| 58 |
+
LLM2Vec-Llama-unsupervised:
|
| 59 |
link: https://huggingface.co/McGill-NLP/LLM2Vec-Llama-2-7b-chat-hf-mntp
|
| 60 |
seq_len: 4096
|
| 61 |
size: 6607
|
|
|
|
| 62 |
dim: 4096
|
| 63 |
is_external: true
|
| 64 |
is_proprietary: false
|
| 65 |
is_sentence_transformers_compatible: false
|
| 66 |
+
LLM2Vec-Mistral-supervised:
|
| 67 |
link: https://huggingface.co/McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-supervised
|
| 68 |
seq_len: 32768
|
| 69 |
size: 7111
|
|
|
|
| 70 |
dim: 4096
|
| 71 |
is_external: true
|
| 72 |
is_proprietary: false
|
| 73 |
is_sentence_transformers_compatible: false
|
| 74 |
+
LLM2Vec-Mistral-unsupervised:
|
| 75 |
link: https://huggingface.co/McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp
|
| 76 |
seq_len: 32768
|
| 77 |
size: 7111
|
| 78 |
+
dim: 4096
|
|
|
|
| 79 |
is_external: true
|
| 80 |
is_proprietary: false
|
| 81 |
is_sentence_transformers_compatible: false
|
| 82 |
+
LLM2Vec-Sheared-Llama-supervised:
|
| 83 |
link: https://huggingface.co/McGill-NLP/LLM2Vec-Sheared-LLaMA-mntp-supervised
|
| 84 |
seq_len: 4096
|
| 85 |
size: 1280
|
|
|
|
| 86 |
dim: 2048
|
| 87 |
is_external: true
|
| 88 |
is_proprietary: false
|
| 89 |
is_sentence_transformers_compatible: false
|
| 90 |
+
LLM2Vec-Sheared-Llama-unsupervised:
|
| 91 |
link: https://huggingface.co/McGill-NLP/LLM2Vec-Sheared-LLaMA-mntp
|
| 92 |
seq_len: 4096
|
| 93 |
size: 1280
|
| 94 |
+
dim: 2048
|
|
|
|
| 95 |
is_external: true
|
| 96 |
is_proprietary: false
|
| 97 |
+
is_sentence_transformers_compatible: false
|
| 98 |
+
LaBSE:
|
| 99 |
link: https://huggingface.co/sentence-transformers/LaBSE
|
| 100 |
seq_len: 512
|
| 101 |
size: 471
|
| 102 |
+
dim: 768
|
| 103 |
+
is_external: true
|
| 104 |
+
is_proprietary: false
|
| 105 |
+
is_sentence_transformers_compatible: true
|
| 106 |
OpenSearch-text-hybrid:
|
| 107 |
+
link: https://help.aliyun.com/zh/open-search/vector-search-edition/hybrid-retrieval
|
| 108 |
+
seq_len: 512
|
| 109 |
+
size: null
|
| 110 |
dim: 1792
|
| 111 |
is_external: true
|
| 112 |
is_proprietary: true
|
| 113 |
is_sentence_transformers_compatible: false
|
|
|
|
|
|
|
|
|
|
| 114 |
all-MiniLM-L12-v2:
|
|
|
|
|
|
|
|
|
|
|
|
|
| 115 |
link: https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2
|
| 116 |
seq_len: 512
|
| 117 |
size: 33
|
|
|
|
| 118 |
dim: 384
|
| 119 |
is_external: true
|
| 120 |
is_proprietary: false
|
| 121 |
is_sentence_transformers_compatible: true
|
| 122 |
+
all-MiniLM-L6-v2:
|
| 123 |
link: https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2
|
| 124 |
seq_len: 512
|
| 125 |
size: 23
|
| 126 |
+
dim: 384
|
|
|
|
| 127 |
is_external: true
|
| 128 |
is_proprietary: false
|
| 129 |
is_sentence_transformers_compatible: true
|
| 130 |
+
all-mpnet-base-v2:
|
| 131 |
link: https://huggingface.co/sentence-transformers/all-mpnet-base-v2
|
| 132 |
seq_len: 514
|
| 133 |
size: 110
|
|
|
|
| 134 |
dim: 768
|
| 135 |
is_external: true
|
| 136 |
is_proprietary: false
|
| 137 |
is_sentence_transformers_compatible: true
|
| 138 |
+
allenai-specter:
|
| 139 |
link: https://huggingface.co/sentence-transformers/allenai-specter
|
| 140 |
seq_len: 512
|
| 141 |
size: 110
|
|
|
|
| 142 |
dim: 768
|
| 143 |
is_external: true
|
| 144 |
is_proprietary: false
|
| 145 |
is_sentence_transformers_compatible: true
|
| 146 |
+
bert-base-10lang-cased:
|
| 147 |
link: https://huggingface.co/Geotrend/bert-base-10lang-cased
|
| 148 |
seq_len: 512
|
| 149 |
size: 138
|
|
|
|
| 150 |
dim: 768
|
| 151 |
is_external: true
|
| 152 |
is_proprietary: false
|
| 153 |
is_sentence_transformers_compatible: true
|
| 154 |
+
bert-base-15lang-cased:
|
| 155 |
link: https://huggingface.co/Geotrend/bert-base-15lang-cased
|
| 156 |
seq_len: 512
|
| 157 |
size: 138
|
|
|
|
| 158 |
dim: 768
|
| 159 |
is_external: true
|
| 160 |
is_proprietary: false
|
| 161 |
is_sentence_transformers_compatible: true
|
| 162 |
+
bert-base-25lang-cased:
|
| 163 |
link: https://huggingface.co/Geotrend/bert-base-25lang-cased
|
| 164 |
seq_len: 512
|
| 165 |
size: 138
|
|
|
|
| 166 |
dim: 768
|
| 167 |
is_external: true
|
| 168 |
is_proprietary: false
|
| 169 |
is_sentence_transformers_compatible: true
|
| 170 |
+
bert-base-multilingual-cased:
|
| 171 |
link: https://huggingface.co/google-bert/bert-base-multilingual-cased
|
| 172 |
seq_len: 512
|
| 173 |
size: 179
|
|
|
|
| 174 |
dim: 768
|
| 175 |
is_external: true
|
| 176 |
is_proprietary: false
|
| 177 |
is_sentence_transformers_compatible: true
|
| 178 |
+
bert-base-multilingual-uncased:
|
| 179 |
link: https://huggingface.co/google-bert/bert-base-multilingual-uncased
|
| 180 |
seq_len: 512
|
| 181 |
size: 168
|
|
|
|
| 182 |
dim: 768
|
| 183 |
is_external: true
|
| 184 |
is_proprietary: false
|
| 185 |
is_sentence_transformers_compatible: true
|
| 186 |
+
bert-base-swedish-cased:
|
| 187 |
link: https://huggingface.co/KB/bert-base-swedish-cased
|
| 188 |
seq_len: 512
|
| 189 |
size: 125
|
|
|
|
| 190 |
dim: 768
|
| 191 |
is_external: true
|
| 192 |
is_proprietary: false
|
| 193 |
is_sentence_transformers_compatible: true
|
| 194 |
+
bert-base-uncased:
|
| 195 |
link: https://huggingface.co/bert-base-uncased
|
| 196 |
seq_len: 512
|
| 197 |
size: 110
|
|
|
|
| 198 |
dim: 768
|
| 199 |
is_external: true
|
| 200 |
is_proprietary: false
|
| 201 |
is_sentence_transformers_compatible: true
|
| 202 |
+
bge-base-zh-v1.5:
|
| 203 |
link: https://huggingface.co/BAAI/bge-base-zh-v1.5
|
| 204 |
seq_len: 512
|
| 205 |
size: 102
|
| 206 |
+
dim: 768
|
|
|
|
| 207 |
is_external: true
|
| 208 |
is_proprietary: false
|
| 209 |
+
is_sentence_transformers_compatible: true
|
| 210 |
+
bge-large-en-v1.5:
|
| 211 |
link: https://huggingface.co/BAAI/bge-large-en-v1.5
|
| 212 |
seq_len: 512
|
| 213 |
size: null
|
|
|
|
| 214 |
dim: 1024
|
| 215 |
is_external: true
|
| 216 |
is_proprietary: false
|
| 217 |
+
is_sentence_transformers_compatible: false
|
| 218 |
+
bge-large-zh-noinstruct:
|
| 219 |
link: https://huggingface.co/BAAI/bge-large-zh-noinstruct
|
| 220 |
seq_len: 512
|
| 221 |
size: 326
|
|
|
|
| 222 |
dim: 1024
|
| 223 |
is_external: true
|
| 224 |
is_proprietary: false
|
| 225 |
is_sentence_transformers_compatible: true
|
| 226 |
+
bge-large-zh-v1.5:
|
| 227 |
link: https://huggingface.co/BAAI/bge-large-zh-v1.5
|
| 228 |
seq_len: 512
|
| 229 |
size: 326
|
| 230 |
+
dim: 1024
|
|
|
|
| 231 |
is_external: true
|
| 232 |
is_proprietary: false
|
| 233 |
is_sentence_transformers_compatible: true
|
| 234 |
+
bge-small-zh-v1.5:
|
| 235 |
link: https://huggingface.co/BAAI/bge-small-zh-v1.5
|
| 236 |
seq_len: 512
|
| 237 |
size: 24
|
|
|
|
| 238 |
dim: 512
|
| 239 |
+
is_external: true
|
| 240 |
is_proprietary: false
|
| 241 |
is_sentence_transformers_compatible: true
|
| 242 |
+
camembert-base:
|
| 243 |
link: https://huggingface.co/almanach/camembert-base
|
| 244 |
seq_len: 512
|
| 245 |
size: 111
|
| 246 |
+
dim: 512
|
|
|
|
| 247 |
is_external: false
|
| 248 |
is_proprietary: false
|
| 249 |
is_sentence_transformers_compatible: true
|
| 250 |
+
camembert-large:
|
| 251 |
link: https://huggingface.co/almanach/camembert-large
|
| 252 |
seq_len: 512
|
| 253 |
size: 338
|
|
|
|
| 254 |
dim: 768
|
| 255 |
+
is_external: false
|
| 256 |
is_proprietary: false
|
| 257 |
is_sentence_transformers_compatible: true
|
| 258 |
+
contriever-base-msmarco:
|
| 259 |
link: https://huggingface.co/nthakur/contriever-base-msmarco
|
| 260 |
seq_len: 512
|
| 261 |
size: 110
|
|
|
|
| 262 |
dim: 768
|
| 263 |
is_external: true
|
| 264 |
is_proprietary: false
|
| 265 |
is_sentence_transformers_compatible: true
|
| 266 |
+
cross-en-de-roberta-sentence-transformer:
|
| 267 |
link: https://huggingface.co/T-Systems-onsite/cross-en-de-roberta-sentence-transformer
|
| 268 |
seq_len: 514
|
| 269 |
size: 278
|
| 270 |
+
dim: 768
|
|
|
|
| 271 |
is_external: true
|
| 272 |
is_proprietary: false
|
| 273 |
is_sentence_transformers_compatible: true
|
| 274 |
+
dfm-encoder-large-v1:
|
| 275 |
link: https://huggingface.co/chcaa/dfm-encoder-large-v1
|
| 276 |
seq_len: 512
|
| 277 |
size: 355
|
|
|
|
| 278 |
dim: 1024
|
| 279 |
is_external: true
|
| 280 |
is_proprietary: false
|
| 281 |
is_sentence_transformers_compatible: true
|
| 282 |
+
dfm-sentence-encoder-large-1:
|
| 283 |
link: https://huggingface.co/chcaa/dfm-encoder-large-v1
|
| 284 |
seq_len: 512
|
| 285 |
size: 355
|
| 286 |
+
dim: 1024
|
| 287 |
+
is_external: true
|
|
|
|
| 288 |
is_proprietary: false
|
| 289 |
is_sentence_transformers_compatible: true
|
| 290 |
+
distilbert-base-25lang-cased:
|
| 291 |
link: https://huggingface.co/Geotrend/distilbert-base-25lang-cased
|
| 292 |
seq_len: 512
|
| 293 |
size: 110
|
|
|
|
| 294 |
dim: 768
|
| 295 |
is_external: false
|
| 296 |
is_proprietary: false
|
| 297 |
is_sentence_transformers_compatible: true
|
| 298 |
+
distilbert-base-en-fr-cased:
|
| 299 |
link: https://huggingface.co/Geotrend/distilbert-base-en-fr-cased
|
| 300 |
seq_len: 512
|
| 301 |
size: 110
|
|
|
|
| 302 |
dim: 768
|
| 303 |
is_external: false
|
| 304 |
is_proprietary: false
|
| 305 |
is_sentence_transformers_compatible: true
|
| 306 |
+
distilbert-base-en-fr-es-pt-it-cased:
|
| 307 |
link: https://huggingface.co/Geotrend/distilbert-base-en-fr-es-pt-it-cased
|
| 308 |
seq_len: 512
|
| 309 |
size: 110
|
|
|
|
| 310 |
dim: 768
|
| 311 |
is_external: false
|
| 312 |
is_proprietary: false
|
| 313 |
is_sentence_transformers_compatible: true
|
| 314 |
+
distilbert-base-fr-cased:
|
| 315 |
link: https://huggingface.co/Geotrend/distilbert-base-fr-cased
|
| 316 |
seq_len: 512
|
| 317 |
size: 110
|
|
|
|
| 318 |
dim: 768
|
| 319 |
is_external: false
|
| 320 |
is_proprietary: false
|
| 321 |
is_sentence_transformers_compatible: true
|
| 322 |
+
distilbert-base-uncased:
|
| 323 |
link: https://huggingface.co/distilbert-base-uncased
|
| 324 |
seq_len: 512
|
| 325 |
size: 110
|
| 326 |
+
dim: 768
|
| 327 |
+
is_external: false
|
|
|
|
| 328 |
is_proprietary: false
|
| 329 |
is_sentence_transformers_compatible: true
|
| 330 |
+
distiluse-base-multilingual-cased-v2:
|
| 331 |
link: https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v2
|
| 332 |
seq_len: 512
|
| 333 |
size: 135
|
| 334 |
+
dim: 512
|
|
|
|
| 335 |
is_external: true
|
| 336 |
is_proprietary: false
|
| 337 |
is_sentence_transformers_compatible: true
|
| 338 |
+
e5-base:
|
| 339 |
link: https://huggingface.co/intfloat/e5-base
|
| 340 |
seq_len: 512
|
| 341 |
size: 110
|
| 342 |
+
dim: 768
|
|
|
|
| 343 |
is_external: true
|
| 344 |
is_proprietary: false
|
| 345 |
is_sentence_transformers_compatible: true
|
| 346 |
+
e5-large:
|
| 347 |
link: https://huggingface.co/intfloat/e5-large
|
| 348 |
seq_len: 512
|
| 349 |
size: 335
|
| 350 |
+
dim: 1024
|
|
|
|
| 351 |
is_external: true
|
| 352 |
is_proprietary: false
|
| 353 |
is_sentence_transformers_compatible: true
|
| 354 |
+
e5-mistral-7b-instruct:
|
| 355 |
link: https://huggingface.co/intfloat/e5-mistral-7b-instruct
|
| 356 |
seq_len: 32768
|
| 357 |
size: 7111
|
| 358 |
+
dim: 4096
|
|
|
|
| 359 |
is_external: true
|
| 360 |
is_proprietary: false
|
| 361 |
is_sentence_transformers_compatible: true
|
| 362 |
+
e5-small:
|
| 363 |
link: https://huggingface.co/intfloat/e5-small
|
| 364 |
seq_len: 512
|
| 365 |
size: 33
|
| 366 |
+
dim: 384
|
|
|
|
| 367 |
is_external: true
|
| 368 |
is_proprietary: false
|
| 369 |
is_sentence_transformers_compatible: true
|
| 370 |
+
electra-small-nordic:
|
| 371 |
link: https://huggingface.co/jonfd/electra-small-nordic
|
| 372 |
seq_len: 512
|
| 373 |
size: 23
|
|
|
|
| 374 |
dim: 256
|
| 375 |
is_external: true
|
| 376 |
is_proprietary: false
|
| 377 |
is_sentence_transformers_compatible: true
|
| 378 |
+
electra-small-swedish-cased-discriminator:
|
| 379 |
link: https://huggingface.co/KBLab/electra-small-swedish-cased-discriminator
|
| 380 |
seq_len: 512
|
| 381 |
size: 16
|
| 382 |
+
dim: 256
|
|
|
|
| 383 |
is_external: true
|
| 384 |
is_proprietary: false
|
| 385 |
is_sentence_transformers_compatible: true
|
| 386 |
+
flaubert_base_cased:
|
| 387 |
link: https://huggingface.co/flaubert/flaubert_base_cased
|
| 388 |
seq_len: 512
|
| 389 |
size: 138
|
|
|
|
| 390 |
dim: 768
|
| 391 |
is_external: true
|
| 392 |
is_proprietary: false
|
| 393 |
is_sentence_transformers_compatible: true
|
| 394 |
+
flaubert_base_uncased:
|
| 395 |
link: https://huggingface.co/flaubert/flaubert_base_uncased
|
| 396 |
seq_len: 512
|
| 397 |
size: 138
|
| 398 |
+
dim: 768
|
|
|
|
| 399 |
is_external: true
|
| 400 |
is_proprietary: false
|
| 401 |
is_sentence_transformers_compatible: true
|
| 402 |
+
flaubert_large_cased:
|
| 403 |
link: https://huggingface.co/flaubert/flaubert_large_cased
|
| 404 |
seq_len: 512
|
| 405 |
size: 372
|
| 406 |
+
dim: 1024
|
|
|
|
| 407 |
is_external: true
|
| 408 |
is_proprietary: false
|
| 409 |
is_sentence_transformers_compatible: true
|
| 410 |
+
gbert-base:
|
| 411 |
link: https://huggingface.co/deepset/gbert-base
|
| 412 |
seq_len: 512
|
| 413 |
size: 110
|
| 414 |
+
dim: 768
|
|
|
|
| 415 |
is_external: true
|
| 416 |
is_proprietary: false
|
| 417 |
is_sentence_transformers_compatible: true
|
| 418 |
+
gbert-large:
|
| 419 |
link: https://huggingface.co/deepset/gbert-large
|
| 420 |
seq_len: 512
|
| 421 |
size: 337
|
| 422 |
+
dim: 1024
|
|
|
|
| 423 |
is_external: true
|
| 424 |
is_proprietary: false
|
| 425 |
is_sentence_transformers_compatible: true
|
| 426 |
+
gelectra-base:
|
| 427 |
link: https://huggingface.co/deepset/gelectra-base
|
| 428 |
seq_len: 512
|
| 429 |
size: 110
|
| 430 |
+
dim: 768
|
|
|
|
| 431 |
is_external: true
|
| 432 |
is_proprietary: false
|
| 433 |
is_sentence_transformers_compatible: true
|
| 434 |
+
gelectra-large:
|
| 435 |
link: https://huggingface.co/deepset/gelectra-large
|
| 436 |
seq_len: 512
|
| 437 |
size: 335
|
| 438 |
+
dim: 1024
|
|
|
|
| 439 |
is_external: true
|
| 440 |
is_proprietary: false
|
| 441 |
is_sentence_transformers_compatible: true
|
| 442 |
+
glove.6B.300d:
|
| 443 |
link: https://huggingface.co/sentence-transformers/average_word_embeddings_glove.6B.300d
|
| 444 |
seq_len: N/A
|
| 445 |
size: 120
|
| 446 |
+
dim: 300
|
| 447 |
+
is_external: true
|
| 448 |
+
is_proprietary: false
|
| 449 |
+
is_sentence_transformers_compatible: true
|
| 450 |
google-gecko-256.text-embedding-preview-0409:
|
| 451 |
+
link: https://cloud.google.com/vertex-ai/generative-ai/docs/embeddings/get-text-embeddings#latest_models
|
| 452 |
+
seq_len: 2048
|
| 453 |
+
size: 1200
|
| 454 |
dim: 256
|
| 455 |
is_external: true
|
| 456 |
is_proprietary: true
|
| 457 |
is_sentence_transformers_compatible: false
|
| 458 |
+
google-gecko.text-embedding-preview-0409:
|
| 459 |
link: https://cloud.google.com/vertex-ai/generative-ai/docs/embeddings/get-text-embeddings#latest_models
|
| 460 |
seq_len: 2048
|
| 461 |
size: 1200
|
|
|
|
| 462 |
dim: 768
|
| 463 |
is_external: true
|
| 464 |
is_proprietary: true
|
| 465 |
is_sentence_transformers_compatible: false
|
|
|
|
|
|
|
|
|
|
| 466 |
gottbert-base:
|
|
|
|
|
|
|
|
|
|
|
|
|
| 467 |
link: https://huggingface.co/uklfr/gottbert-base
|
| 468 |
seq_len: 512
|
| 469 |
size: 127
|
|
|
|
| 470 |
dim: 768
|
| 471 |
is_external: true
|
| 472 |
is_proprietary: false
|
| 473 |
is_sentence_transformers_compatible: true
|
| 474 |
+
gtr-t5-base:
|
| 475 |
link: https://huggingface.co/sentence-transformers/gtr-t5-base
|
| 476 |
seq_len: 512
|
| 477 |
size: 110
|
|
|
|
| 478 |
dim: 768
|
| 479 |
is_external: true
|
| 480 |
is_proprietary: false
|
| 481 |
is_sentence_transformers_compatible: true
|
| 482 |
+
gtr-t5-large:
|
| 483 |
link: https://huggingface.co/sentence-transformers/gtr-t5-large
|
| 484 |
seq_len: 512
|
| 485 |
size: 168
|
|
|
|
| 486 |
dim: 768
|
| 487 |
is_external: true
|
| 488 |
is_proprietary: false
|
| 489 |
is_sentence_transformers_compatible: true
|
| 490 |
+
gtr-t5-xl:
|
| 491 |
link: https://huggingface.co/sentence-transformers/gtr-t5-xl
|
| 492 |
seq_len: 512
|
| 493 |
size: 1240
|
|
|
|
| 494 |
dim: 768
|
| 495 |
is_external: true
|
| 496 |
is_proprietary: false
|
| 497 |
is_sentence_transformers_compatible: true
|
| 498 |
+
gtr-t5-xxl:
|
| 499 |
link: https://huggingface.co/sentence-transformers/gtr-t5-xxl
|
| 500 |
seq_len: 512
|
| 501 |
size: 4865
|
|
|
|
| 502 |
dim: 768
|
| 503 |
is_external: true
|
| 504 |
is_proprietary: false
|
| 505 |
is_sentence_transformers_compatible: true
|
| 506 |
+
herbert-base-retrieval-v2:
|
| 507 |
link: https://huggingface.co/ipipan/herbert-base-retrieval-v2
|
| 508 |
seq_len: 514
|
| 509 |
size: 125
|
| 510 |
+
dim: 768
|
|
|
|
| 511 |
is_external: true
|
| 512 |
is_proprietary: false
|
| 513 |
is_sentence_transformers_compatible: true
|
| 514 |
+
komninos:
|
| 515 |
link: https://huggingface.co/sentence-transformers/average_word_embeddings_komninos
|
| 516 |
seq_len: N/A
|
| 517 |
size: 134
|
| 518 |
+
dim: 300
|
|
|
|
| 519 |
is_external: true
|
| 520 |
is_proprietary: false
|
| 521 |
is_sentence_transformers_compatible: true
|
| 522 |
+
luotuo-bert-medium:
|
| 523 |
link: https://huggingface.co/silk-road/luotuo-bert-medium
|
| 524 |
seq_len: 512
|
| 525 |
size: 328
|
|
|
|
| 526 |
dim: 768
|
| 527 |
is_external: true
|
| 528 |
is_proprietary: false
|
| 529 |
is_sentence_transformers_compatible: true
|
| 530 |
+
m3e-base:
|
| 531 |
link: https://huggingface.co/moka-ai/m3e-base
|
| 532 |
seq_len: 512
|
| 533 |
size: 102
|
|
|
|
| 534 |
dim: 768
|
| 535 |
is_external: true
|
| 536 |
is_proprietary: false
|
| 537 |
is_sentence_transformers_compatible: true
|
| 538 |
+
m3e-large:
|
| 539 |
link: https://huggingface.co/moka-ai/m3e-large
|
| 540 |
seq_len: 512
|
| 541 |
size: 102
|
| 542 |
+
dim: 768
|
| 543 |
+
is_external: true
|
| 544 |
+
is_proprietary: false
|
| 545 |
+
is_sentence_transformers_compatible: true
|
| 546 |
mistral-embed:
|
| 547 |
+
link: https://docs.mistral.ai/guides/embeddings
|
| 548 |
+
seq_len: null
|
| 549 |
+
size: null
|
| 550 |
dim: 1024
|
| 551 |
is_external: true
|
| 552 |
is_proprietary: true
|
| 553 |
is_sentence_transformers_compatible: false
|
|
|
|
|
|
|
|
|
|
| 554 |
msmarco-bert-co-condensor:
|
|
|
|
|
|
|
|
|
|
|
|
|
| 555 |
link: https://huggingface.co/sentence-transformers/msmarco-bert-co-condensor
|
| 556 |
seq_len: 512
|
| 557 |
size: 110
|
| 558 |
+
dim: 768
|
|
|
|
| 559 |
is_external: true
|
| 560 |
is_proprietary: false
|
| 561 |
is_sentence_transformers_compatible: true
|
| 562 |
+
multi-qa-MiniLM-L6-cos-v1:
|
| 563 |
link: https://huggingface.co/sentence-transformers/multi-qa-MiniLM-L6-cos-v1
|
| 564 |
seq_len: 512
|
| 565 |
size: 23
|
| 566 |
+
dim: 384
|
|
|
|
| 567 |
is_external: true
|
| 568 |
is_proprietary: false
|
| 569 |
is_sentence_transformers_compatible: true
|
| 570 |
+
multilingual-e5-base:
|
| 571 |
link: https://huggingface.co/intfloat/multilingual-e5-base
|
| 572 |
seq_len: 514
|
| 573 |
size: 278
|
| 574 |
+
dim: 768
|
|
|
|
| 575 |
is_external: true
|
| 576 |
is_proprietary: false
|
| 577 |
is_sentence_transformers_compatible: true
|
| 578 |
+
multilingual-e5-large:
|
| 579 |
link: https://huggingface.co/intfloat/multilingual-e5-large
|
| 580 |
seq_len: 514
|
| 581 |
size: 560
|
| 582 |
+
dim: 1024
|
|
|
|
| 583 |
is_external: true
|
| 584 |
is_proprietary: false
|
| 585 |
is_sentence_transformers_compatible: true
|
| 586 |
+
multilingual-e5-small:
|
| 587 |
link: https://huggingface.co/intfloat/multilingual-e5-small
|
| 588 |
seq_len: 512
|
| 589 |
size: 118
|
| 590 |
+
dim: 384
|
|
|
|
| 591 |
is_external: true
|
| 592 |
is_proprietary: false
|
| 593 |
is_sentence_transformers_compatible: true
|
| 594 |
+
nb-bert-base:
|
| 595 |
link: https://huggingface.co/NbAiLab/nb-bert-base
|
| 596 |
seq_len: 512
|
| 597 |
size: 179
|
| 598 |
+
dim: 768
|
|
|
|
| 599 |
is_external: true
|
| 600 |
is_proprietary: false
|
| 601 |
is_sentence_transformers_compatible: true
|
| 602 |
+
nb-bert-large:
|
| 603 |
link: https://huggingface.co/NbAiLab/nb-bert-large
|
| 604 |
seq_len: 512
|
| 605 |
size: 355
|
| 606 |
+
dim: 1024
|
|
|
|
| 607 |
is_external: true
|
| 608 |
is_proprietary: false
|
| 609 |
is_sentence_transformers_compatible: true
|
| 610 |
+
nomic-embed-text-v1.5-128:
|
| 611 |
link: https://huggingface.co/nomic-ai/nomic-embed-text-v1.5
|
| 612 |
seq_len: 8192
|
| 613 |
size: 138
|
| 614 |
+
dim: 128
|
|
|
|
| 615 |
is_external: true
|
| 616 |
is_proprietary: false
|
| 617 |
is_sentence_transformers_compatible: true
|
| 618 |
+
nomic-embed-text-v1.5-256:
|
| 619 |
link: https://huggingface.co/nomic-ai/nomic-embed-text-v1.5
|
| 620 |
seq_len: 8192
|
| 621 |
size: 138
|
| 622 |
+
dim: 256
|
|
|
|
| 623 |
is_external: true
|
| 624 |
is_proprietary: false
|
| 625 |
is_sentence_transformers_compatible: true
|
| 626 |
+
nomic-embed-text-v1.5-512:
|
| 627 |
link: https://huggingface.co/nomic-ai/nomic-embed-text-v1.5
|
| 628 |
seq_len: 8192
|
| 629 |
size: 138
|
| 630 |
+
dim: 512
|
|
|
|
| 631 |
is_external: true
|
| 632 |
is_proprietary: false
|
| 633 |
is_sentence_transformers_compatible: true
|
| 634 |
+
nomic-embed-text-v1.5-64:
|
| 635 |
link: https://huggingface.co/nomic-ai/nomic-embed-text-v1.5
|
| 636 |
seq_len: 8192
|
| 637 |
size: 138
|
| 638 |
+
dim: 64
|
|
|
|
| 639 |
is_external: true
|
| 640 |
is_proprietary: false
|
| 641 |
is_sentence_transformers_compatible: true
|
| 642 |
+
norbert3-base:
|
| 643 |
link: https://huggingface.co/ltg/norbert3-base
|
| 644 |
seq_len: 512
|
| 645 |
size: 131
|
| 646 |
+
dim: 768
|
|
|
|
| 647 |
is_external: true
|
| 648 |
is_proprietary: false
|
| 649 |
is_sentence_transformers_compatible: true
|
| 650 |
+
norbert3-large:
|
| 651 |
link: https://huggingface.co/ltg/norbert3-large
|
| 652 |
seq_len: 512
|
| 653 |
size: 368
|
| 654 |
+
dim: 1024
|
|
|
|
| 655 |
is_external: true
|
| 656 |
is_proprietary: false
|
| 657 |
is_sentence_transformers_compatible: true
|
| 658 |
+
paraphrase-multilingual-MiniLM-L12-v2:
|
| 659 |
link: https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
|
| 660 |
seq_len: 512
|
| 661 |
size: 118
|
| 662 |
+
dim: 384
|
|
|
|
| 663 |
is_external: true
|
| 664 |
is_proprietary: false
|
| 665 |
is_sentence_transformers_compatible: true
|
| 666 |
+
paraphrase-multilingual-mpnet-base-v2:
|
| 667 |
link: https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2
|
| 668 |
seq_len: 514
|
| 669 |
size: 278
|
|
|
|
| 670 |
dim: 768
|
| 671 |
is_external: true
|
| 672 |
is_proprietary: false
|
| 673 |
is_sentence_transformers_compatible: true
|
| 674 |
+
sentence-bert-swedish-cased:
|
| 675 |
link: https://huggingface.co/KBLab/sentence-bert-swedish-cased
|
| 676 |
seq_len: 512
|
| 677 |
size: 125
|
|
|
|
| 678 |
dim: 768
|
| 679 |
is_external: true
|
| 680 |
is_proprietary: false
|
| 681 |
is_sentence_transformers_compatible: true
|
| 682 |
+
sentence-camembert-base:
|
| 683 |
link: https://huggingface.co/dangvantuan/sentence-camembert-base
|
| 684 |
seq_len: 512
|
| 685 |
size: 110
|
| 686 |
+
dim: 768
|
|
|
|
| 687 |
is_external: true
|
| 688 |
is_proprietary: false
|
| 689 |
is_sentence_transformers_compatible: true
|
| 690 |
+
sentence-camembert-large:
|
| 691 |
link: https://huggingface.co/dangvantuan/sentence-camembert-large
|
| 692 |
seq_len: 512
|
| 693 |
size: 337
|
| 694 |
+
dim: 1024
|
|
|
|
| 695 |
is_external: true
|
| 696 |
is_proprietary: false
|
| 697 |
is_sentence_transformers_compatible: true
|
| 698 |
+
sentence-croissant-llm-base:
|
| 699 |
link: https://huggingface.co/Wissam42/sentence-croissant-llm-base
|
| 700 |
seq_len: 2048
|
| 701 |
size: 1280
|
| 702 |
+
dim: 2048
|
|
|
|
| 703 |
is_external: true
|
| 704 |
is_proprietary: false
|
| 705 |
is_sentence_transformers_compatible: true
|
| 706 |
+
sentence-t5-base:
|
| 707 |
link: https://huggingface.co/sentence-transformers/sentence-t5-base
|
| 708 |
seq_len: 512
|
| 709 |
size: 110
|
|
|
|
| 710 |
dim: 768
|
| 711 |
is_external: true
|
| 712 |
is_proprietary: false
|
| 713 |
is_sentence_transformers_compatible: true
|
| 714 |
+
sentence-t5-large:
|
| 715 |
link: https://huggingface.co/sentence-transformers/sentence-t5-large
|
| 716 |
seq_len: 512
|
| 717 |
size: 168
|
|
|
|
| 718 |
dim: 768
|
| 719 |
is_external: true
|
| 720 |
is_proprietary: false
|
| 721 |
is_sentence_transformers_compatible: true
|
| 722 |
+
sentence-t5-xl:
|
| 723 |
link: https://huggingface.co/sentence-transformers/sentence-t5-xl
|
| 724 |
seq_len: 512
|
| 725 |
size: 1240
|
|
|
|
| 726 |
dim: 768
|
| 727 |
is_external: true
|
| 728 |
is_proprietary: false
|
| 729 |
is_sentence_transformers_compatible: true
|
| 730 |
+
sentence-t5-xxl:
|
| 731 |
link: https://huggingface.co/sentence-transformers/sentence-t5-xxl
|
| 732 |
seq_len: 512
|
| 733 |
size: 4865
|
|
|
|
| 734 |
dim: 768
|
| 735 |
is_external: true
|
| 736 |
is_proprietary: false
|
| 737 |
is_sentence_transformers_compatible: true
|
| 738 |
+
silver-retriever-base-v1:
|
| 739 |
link: https://huggingface.co/ipipan/silver-retriever-base-v1
|
| 740 |
seq_len: 514
|
| 741 |
size: 125
|
|
|
|
| 742 |
dim: 768
|
| 743 |
is_external: true
|
| 744 |
is_proprietary: false
|
| 745 |
is_sentence_transformers_compatible: true
|
| 746 |
+
st-polish-paraphrase-from-distilroberta:
|
| 747 |
link: https://huggingface.co/sdadas/st-polish-paraphrase-from-distilroberta
|
| 748 |
seq_len: 514
|
| 749 |
size: 125
|
|
|
|
| 750 |
dim: 768
|
| 751 |
is_external: true
|
| 752 |
is_proprietary: false
|
| 753 |
is_sentence_transformers_compatible: true
|
| 754 |
+
st-polish-paraphrase-from-mpnet:
|
| 755 |
link: https://huggingface.co/sdadas/st-polish-paraphrase-from-mpnet
|
| 756 |
seq_len: 514
|
| 757 |
size: 125
|
|
|
|
| 758 |
dim: 768
|
| 759 |
is_external: true
|
| 760 |
is_proprietary: false
|
| 761 |
is_sentence_transformers_compatible: true
|
| 762 |
+
sup-simcse-bert-base-uncased:
|
| 763 |
link: https://huggingface.co/princeton-nlp/sup-simcse-bert-base-uncased
|
| 764 |
seq_len: 512
|
| 765 |
size: 110
|
| 766 |
+
dim: 768
|
| 767 |
+
is_external: true
|
| 768 |
+
is_proprietary: false
|
| 769 |
+
is_sentence_transformers_compatible: true
|
| 770 |
text-embedding-3-large:
|
| 771 |
+
link: https://openai.com/blog/new-embedding-models-and-api-updates
|
| 772 |
+
seq_len: 8191
|
| 773 |
+
size: null
|
| 774 |
dim: 3072
|
| 775 |
is_external: true
|
| 776 |
is_proprietary: true
|
| 777 |
is_sentence_transformers_compatible: false
|
| 778 |
+
text-embedding-3-large-256:
|
| 779 |
link: https://openai.com/blog/new-embedding-models-and-api-updates
|
| 780 |
seq_len: 8191
|
| 781 |
size: null
|
|
|
|
| 782 |
dim: 256
|
| 783 |
is_external: true
|
| 784 |
is_proprietary: true
|
| 785 |
is_sentence_transformers_compatible: false
|
| 786 |
+
text-embedding-3-small:
|
| 787 |
link: https://openai.com/blog/new-embedding-models-and-api-updates
|
| 788 |
seq_len: 8191
|
| 789 |
size: null
|
|
|
|
| 790 |
dim: 1536
|
| 791 |
is_external: true
|
| 792 |
is_proprietary: true
|
| 793 |
is_sentence_transformers_compatible: false
|
| 794 |
+
text-embedding-ada-002:
|
| 795 |
+
link: https://openai.com/blog/new-and-improved-embedding-model
|
| 796 |
seq_len: 8191
|
| 797 |
size: null
|
|
|
|
| 798 |
dim: 1536
|
| 799 |
is_external: true
|
| 800 |
is_proprietary: true
|
| 801 |
is_sentence_transformers_compatible: false
|
|
|
|
|
|
|
|
|
|
| 802 |
text-search-ada-001:
|
| 803 |
+
link: https://openai.com/blog/introducing-text-and-code-embeddings
|
| 804 |
+
seq_len: 2046
|
| 805 |
+
size: null
|
| 806 |
dim: 1024
|
| 807 |
is_external: true
|
| 808 |
is_proprietary: true
|
| 809 |
is_sentence_transformers_compatible: false
|
| 810 |
+
text-search-ada-doc-001:
|
| 811 |
link: https://openai.com/blog/introducing-text-and-code-embeddings
|
| 812 |
seq_len: 2046
|
| 813 |
size: null
|
|
|
|
| 814 |
dim: 1024
|
| 815 |
is_external: true
|
| 816 |
is_proprietary: true
|
| 817 |
is_sentence_transformers_compatible: false
|
| 818 |
+
text-search-ada-query-001:
|
| 819 |
link: https://openai.com/blog/introducing-text-and-code-embeddings
|
| 820 |
seq_len: 2046
|
| 821 |
size: null
|
|
|
|
| 822 |
dim: 1024
|
| 823 |
is_external: false
|
| 824 |
is_proprietary: true
|
| 825 |
is_sentence_transformers_compatible: false
|
| 826 |
+
text-search-babbage-001:
|
| 827 |
link: https://openai.com/blog/introducing-text-and-code-embeddings
|
| 828 |
seq_len: 2046
|
| 829 |
size: null
|
|
|
|
| 830 |
dim: 2048
|
| 831 |
is_external: true
|
| 832 |
is_proprietary: true
|
| 833 |
is_sentence_transformers_compatible: false
|
| 834 |
+
text-search-curie-001:
|
| 835 |
link: https://openai.com/blog/introducing-text-and-code-embeddings
|
| 836 |
seq_len: 2046
|
| 837 |
size: null
|
|
|
|
| 838 |
dim: 4096
|
| 839 |
is_external: true
|
| 840 |
is_proprietary: true
|
| 841 |
is_sentence_transformers_compatible: false
|
| 842 |
+
text-search-davinci-001:
|
| 843 |
link: https://openai.com/blog/introducing-text-and-code-embeddings
|
| 844 |
seq_len: 2046
|
| 845 |
size: null
|
|
|
|
| 846 |
dim: 12288
|
| 847 |
is_external: true
|
| 848 |
is_proprietary: true
|
| 849 |
is_sentence_transformers_compatible: false
|
| 850 |
+
text-similarity-ada-001:
|
| 851 |
link: https://openai.com/blog/introducing-text-and-code-embeddings
|
| 852 |
seq_len: 2046
|
| 853 |
size: null
|
|
|
|
| 854 |
dim: 1024
|
| 855 |
is_external: true
|
| 856 |
is_proprietary: true
|
| 857 |
is_sentence_transformers_compatible: false
|
| 858 |
+
text-similarity-babbage-001:
|
| 859 |
link: https://openai.com/blog/introducing-text-and-code-embeddings
|
| 860 |
seq_len: 2046
|
| 861 |
size: null
|
|
|
|
| 862 |
dim: 2048
|
| 863 |
is_external: true
|
| 864 |
is_proprietary: true
|
| 865 |
is_sentence_transformers_compatible: false
|
| 866 |
+
text-similarity-curie-001:
|
| 867 |
link: https://openai.com/blog/introducing-text-and-code-embeddings
|
| 868 |
seq_len: 2046
|
| 869 |
size: null
|
|
|
|
| 870 |
dim: 4096
|
| 871 |
is_external: true
|
| 872 |
is_proprietary: true
|
| 873 |
is_sentence_transformers_compatible: false
|
| 874 |
+
text-similarity-davinci-001:
|
| 875 |
link: https://openai.com/blog/introducing-text-and-code-embeddings
|
| 876 |
seq_len: 2046
|
| 877 |
size: null
|
|
|
|
| 878 |
dim: 12288
|
| 879 |
is_external: true
|
| 880 |
is_proprietary: true
|
| 881 |
is_sentence_transformers_compatible: false
|
|
|
|
|
|
|
|
|
|
| 882 |
text2vec-base-chinese:
|
| 883 |
+
link: https://huggingface.co/shibing624/text2vec-base-chinese
|
| 884 |
+
seq_len: 512
|
| 885 |
+
size: 102
|
| 886 |
dim: 768
|
| 887 |
is_external: true
|
| 888 |
is_proprietary: false
|
| 889 |
is_sentence_transformers_compatible: true
|
|
|
|
|
|
|
|
|
|
| 890 |
text2vec-base-multilingual:
|
| 891 |
+
link: null
|
| 892 |
+
seq_len: null
|
| 893 |
+
size: null
|
| 894 |
dim: null
|
| 895 |
is_external: true
|
| 896 |
is_proprietary: false
|
| 897 |
is_sentence_transformers_compatible: false
|
|
|
|
|
|
|
|
|
|
| 898 |
text2vec-large-chinese:
|
| 899 |
+
link: https://huggingface.co/GanymedeNil/text2vec-large-chinese
|
| 900 |
+
seq_len: 512
|
| 901 |
+
size: 326
|
| 902 |
dim: 1024
|
| 903 |
is_external: true
|
| 904 |
is_proprietary: false
|
| 905 |
is_sentence_transformers_compatible: true
|
|
|
|
|
|
|
|
|
|
| 906 |
titan-embed-text-v1:
|
|
|
|
|
|
|
|
|
|
|
|
|
| 907 |
link: https://docs.aws.amazon.com/bedrock/latest/userguide/embeddings.html
|
| 908 |
seq_len: 8000
|
| 909 |
size: null
|
|
|
|
| 910 |
dim: 1536
|
| 911 |
is_external: true
|
| 912 |
+
is_proprietary: true
|
| 913 |
+
is_sentence_transformers_compatible: false
|
| 914 |
+
udever-bloom-1b1:
|
| 915 |
link: https://huggingface.co/izhx/udever-bloom-1b1
|
| 916 |
seq_len: 2048
|
| 917 |
size: null
|
| 918 |
+
dim: 1536
|
|
|
|
| 919 |
is_external: true
|
| 920 |
is_proprietary: false
|
| 921 |
is_sentence_transformers_compatible: true
|
| 922 |
+
udever-bloom-560m:
|
| 923 |
link: https://huggingface.co/izhx/udever-bloom-560m
|
| 924 |
seq_len: 2048
|
| 925 |
size: null
|
| 926 |
+
dim: 1024
|
|
|
|
| 927 |
is_external: true
|
| 928 |
is_proprietary: false
|
| 929 |
is_sentence_transformers_compatible: true
|
| 930 |
+
universal-sentence-encoder-multilingual-3:
|
| 931 |
link: https://huggingface.co/vprelovac/universal-sentence-encoder-multilingual-3
|
| 932 |
seq_len: 512
|
| 933 |
size: null
|
|
|
|
| 934 |
dim: 512
|
| 935 |
is_external: true
|
| 936 |
is_proprietary: false
|
| 937 |
is_sentence_transformers_compatible: true
|
| 938 |
+
universal-sentence-encoder-multilingual-large-3:
|
| 939 |
link: https://huggingface.co/vprelovac/universal-sentence-encoder-multilingual-large-3
|
| 940 |
seq_len: 512
|
| 941 |
size: null
|
| 942 |
+
dim: 512
|
|
|
|
| 943 |
is_external: true
|
| 944 |
is_proprietary: false
|
| 945 |
is_sentence_transformers_compatible: true
|
| 946 |
+
unsup-simcse-bert-base-uncased:
|
| 947 |
link: https://huggingface.co/princeton-nlp/unsup-simcse-bert-base-uncased
|
| 948 |
seq_len: 512
|
| 949 |
size: 110
|
|
|
|
| 950 |
dim: 768
|
| 951 |
is_external: true
|
| 952 |
is_proprietary: false
|
| 953 |
is_sentence_transformers_compatible: true
|
| 954 |
+
use-cmlm-multilingual:
|
| 955 |
link: https://huggingface.co/sentence-transformers/use-cmlm-multilingual
|
| 956 |
seq_len: 512
|
| 957 |
size: 472
|
| 958 |
+
dim: 768
|
| 959 |
+
is_external: true
|
| 960 |
+
is_proprietary: false
|
| 961 |
+
is_sentence_transformers_compatible: true
|
| 962 |
voyage-2:
|
| 963 |
+
link: https://docs.voyageai.com/embeddings/
|
| 964 |
+
seq_len: 1024
|
| 965 |
+
size: null
|
| 966 |
dim: 1024
|
| 967 |
is_external: true
|
| 968 |
is_proprietary: true
|
| 969 |
is_sentence_transformers_compatible: false
|
| 970 |
+
voyage-code-2:
|
| 971 |
link: https://docs.voyageai.com/embeddings/
|
| 972 |
+
seq_len: 16000
|
| 973 |
size: null
|
|
|
|
| 974 |
dim: 1536
|
| 975 |
is_external: true
|
| 976 |
is_proprietary: true
|
| 977 |
is_sentence_transformers_compatible: false
|
| 978 |
+
voyage-large-2-instruct:
|
| 979 |
link: https://docs.voyageai.com/embeddings/
|
| 980 |
seq_len: 16000
|
| 981 |
size: null
|
|
|
|
| 982 |
dim: 1024
|
| 983 |
is_external: true
|
| 984 |
is_proprietary: false
|
| 985 |
is_sentence_transformers_compatible: false
|
| 986 |
+
voyage-law-2:
|
| 987 |
link: https://docs.voyageai.com/embeddings/
|
| 988 |
+
seq_len: 4000
|
| 989 |
size: null
|
|
|
|
| 990 |
dim: 1024
|
| 991 |
is_external: true
|
| 992 |
is_proprietary: true
|
| 993 |
is_sentence_transformers_compatible: false
|
| 994 |
+
voyage-lite-01-instruct:
|
| 995 |
link: https://docs.voyageai.com/embeddings/
|
| 996 |
seq_len: 4000
|
| 997 |
size: null
|
|
|
|
| 998 |
dim: 1024
|
| 999 |
is_external: true
|
| 1000 |
is_proprietary: true
|
| 1001 |
is_sentence_transformers_compatible: false
|
| 1002 |
+
voyage-lite-02-instruct:
|
| 1003 |
link: https://docs.voyageai.com/embeddings/
|
| 1004 |
seq_len: 4000
|
| 1005 |
+
size: 1220
|
|
|
|
| 1006 |
dim: 1024
|
| 1007 |
is_external: true
|
| 1008 |
is_proprietary: true
|
| 1009 |
is_sentence_transformers_compatible: false
|
|
|
|
|
|
|
|
|
|
| 1010 |
xlm-roberta-base:
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1011 |
link: https://huggingface.co/xlm-roberta-base
|
| 1012 |
seq_len: 514
|
| 1013 |
size: 279
|
| 1014 |
+
dim: 768
|
|
|
|
| 1015 |
is_external: true
|
| 1016 |
is_proprietary: false
|
| 1017 |
is_sentence_transformers_compatible: true
|
| 1018 |
+
xlm-roberta-large:
|
| 1019 |
link: https://huggingface.co/xlm-roberta-large
|
| 1020 |
seq_len: 514
|
| 1021 |
size: 560
|
| 1022 |
+
dim: 1024
|
| 1023 |
+
is_external: true
|
| 1024 |
+
is_proprietary: false
|
| 1025 |
+
is_sentence_transformers_compatible: true
|
| 1026 |
models_to_skip:
|
| 1027 |
- michaelfeil/ct2fast-e5-large-v2
|
| 1028 |
- McGill-NLP/LLM2Vec-Sheared-LLaMA-mntp-unsup-simcse
|