mteb 2.5.2__py3-none-any.whl → 2.7.9__py3-none-any.whl

mteb/models/model_implementations/ru_sentence_models.py

@@ -244,13 +244,14 @@ rubert_tiny = ModelMeta(
     revision="5441c5ea8026d4f6d7505ec004845409f1259fb1",
     release_date="2021-05-24",
     n_parameters=11_900_000,
+    n_embedding_parameters=9_223_968,
     memory_usage_mb=45,
     embed_dim=312,
     license="mit",
     max_tokens=512,
     reference="https://huggingface.co/cointegrated/rubert-tiny",
     similarity_fn_name=ScoringFunction.COSINE,
-    framework=["Sentence Transformers", "PyTorch"],
+    framework=["Sentence Transformers", "PyTorch", "Transformers", "safetensors"],
     use_instructions=False,
     public_training_code="https://gist.github.com/avidale/7bc6350f26196918bf339c01261f5c60",
     training_datasets={
@@ -270,13 +271,14 @@ rubert_tiny2 = ModelMeta(
     revision="dad72b8f77c5eef6995dd3e4691b758ba56b90c3",
     release_date="2021-10-28",
     n_parameters=29_400_000,
+    n_embedding_parameters=26_154_336,
     memory_usage_mb=112,
     embed_dim=312,
     license="mit",
     max_tokens=2048,
     reference="https://huggingface.co/cointegrated/rubert-tiny2",
     similarity_fn_name=ScoringFunction.COSINE,
-    framework=["Sentence Transformers", "PyTorch"],
+    framework=["Sentence Transformers", "PyTorch", "safetensors", "Transformers"],
     use_instructions=False,
     public_training_code="https://colab.research.google.com/drive/1mSWfIQ6PIlteLVZ9DKKpcorycgLIKZLf?usp=sharing",
     training_datasets=set(
@@ -297,13 +299,14 @@ sbert_large_nlu_ru = ModelMeta(
     revision="af977d5dfa46a3635e29bf0ef383f2df2a08d47a",
     release_date="2020-11-20",
     n_parameters=427_000_000,
+    n_embedding_parameters=123_021_312,
     memory_usage_mb=1629,
     embed_dim=1024,
     license="mit",
     max_tokens=512,  # best guess
     reference="https://huggingface.co/ai-forever/sbert_large_nlu_ru",
     similarity_fn_name=ScoringFunction.COSINE,
-    framework=["Sentence Transformers", "PyTorch"],
+    framework=["Sentence Transformers", "PyTorch", "Transformers", "safetensors"],
     use_instructions=False,
     public_training_code=None,
     public_training_data=None,
@@ -323,13 +326,14 @@ sbert_large_mt_nlu_ru = ModelMeta(
     revision="05300876c2b83f46d3ddd422a7f17e45cf633bb0",
     release_date="2021-05-18",
     n_parameters=427_000_000,
+    n_embedding_parameters=123_021_312,
     memory_usage_mb=1629,
     embed_dim=1024,
     license="not specified",
     max_tokens=512,  # best guess
     reference="https://huggingface.co/ai-forever/sbert_large_mt_nlu_ru",
     similarity_fn_name=ScoringFunction.COSINE,
-    framework=["Sentence Transformers", "PyTorch"],
+    framework=["Sentence Transformers", "PyTorch", "Transformers", "safetensors"],
     use_instructions=False,
     public_training_code=None,
     public_training_data=None,
@@ -351,13 +355,14 @@ user_base_ru = ModelMeta(
     revision="436a489a2087d61aa670b3496a9915f84e46c861",
     release_date="2024-06-10",
     n_parameters=427_000_000,
+    n_embedding_parameters=38_603_520,
     memory_usage_mb=473,
     embed_dim=768,
     license="apache-2.0",
     max_tokens=512,
     reference="https://huggingface.co/deepvk/USER-base",
     similarity_fn_name=ScoringFunction.COSINE,
-    framework=["Sentence Transformers", "PyTorch"],
+    framework=["Sentence Transformers", "PyTorch", "safetensors"],
     adapted_from="https://huggingface.co/deepvk/deberta-v1-base",
     use_instructions=True,
     citation="""@misc{deepvk2024user,
@@ -412,13 +417,14 @@ user_bge_m3 = ModelMeta(
     revision="0cc6cfe48e260fb0474c753087a69369e88709ae",
     release_date="2024-07-05",
     n_parameters=359_026_688,
+    n_embedding_parameters=47_273_984,
     memory_usage_mb=1370,
     embed_dim=1024,
     license="apache-2.0",
     max_tokens=8194,
     reference="https://huggingface.co/deepvk/USER-base",
     similarity_fn_name=ScoringFunction.COSINE,
-    framework=["Sentence Transformers", "PyTorch"],
+    framework=["Sentence Transformers", "PyTorch", "safetensors"],
     adapted_from="BAAI/bge-m3",
     use_instructions=False,
     training_datasets={
@@ -463,13 +469,14 @@ deberta_v1_ru = ModelMeta(
     revision="bdd30b0e19757e6940c92c7aff19e8fc0a60dff4",
     release_date="2023-02-07",
     n_parameters=124_000_000,
+    n_embedding_parameters=38_603_520,
     memory_usage_mb=473,
     embed_dim=768,
     license="apache-2.0",
     max_tokens=512,
     reference="https://huggingface.co/deepvk/deberta-v1-base",
     similarity_fn_name=ScoringFunction.COSINE,
-    framework=["Sentence Transformers", "PyTorch"],
+    framework=["Sentence Transformers", "PyTorch", "Transformers", "safetensors"],
     use_instructions=False,
     # Wikipedia, Books, Twitter comments, Pikabu, Proza.ru, Film subtitles, News websites, and Social corpus
     public_training_code=None,
@@ -494,13 +501,14 @@ rubert_base_cased = ModelMeta(
     revision="4036cab694767a299f2b9e6492909664d9414229",
     release_date="2020-03-04",
     n_parameters=1280_000_000,
+    n_embedding_parameters=91_812_096,
     memory_usage_mb=4883,
     embed_dim=768,
     license="not specified",
     max_tokens=512,
     reference="https://huggingface.co/DeepPavlov/rubert-base-cased",
     similarity_fn_name=ScoringFunction.COSINE,
-    framework=["Sentence Transformers", "PyTorch"],
+    framework=["Sentence Transformers", "PyTorch", "Transformers"],
     use_instructions=False,
     public_training_code=None,
     public_training_data=None,
@@ -530,13 +538,14 @@ distilrubert_small_cased_conversational = ModelMeta(
     revision="e348066b4a7279b97138038299bddc6580a9169a",
     release_date="2022-06-28",
     n_parameters=107_000_000,
+    n_embedding_parameters=91_812_096,
     memory_usage_mb=408,
     embed_dim=768,
     license="not specified",
     max_tokens=512,
     reference="https://huggingface.co/DeepPavlov/distilrubert-small-cased-conversational",
     similarity_fn_name=ScoringFunction.COSINE,
-    framework=["Sentence Transformers", "PyTorch"],
+    framework=["Sentence Transformers", "PyTorch", "Transformers"],
     use_instructions=False,
     public_training_code=None,
     public_training_data=None,
@@ -565,13 +574,14 @@ rubert_base_cased_sentence = ModelMeta(
     revision="78b5122d6365337dd4114281b0d08cd1edbb3bc8",
     release_date="2020-03-04",
     n_parameters=107_000_000,
+    n_embedding_parameters=91_812_096,
     memory_usage_mb=408,
     embed_dim=768,
     license="not specified",
     max_tokens=512,
     reference="https://huggingface.co/DeepPavlov/rubert-base-cased-sentence",
     similarity_fn_name=ScoringFunction.COSINE,
-    framework=["Sentence Transformers", "PyTorch"],
+    framework=["Sentence Transformers", "PyTorch", "Transformers"],
     use_instructions=False,
     public_training_code=None,
     public_training_data=None,
@@ -590,13 +600,14 @@ labse_en_ru = ModelMeta(
     revision="cf0714e606d4af551e14ad69a7929cd6b0da7f7e",
     release_date="2021-06-10",
     n_parameters=129_000_000,
+    n_embedding_parameters=42_303_744,
     memory_usage_mb=492,
     embed_dim=768,
     license="not specified",
     max_tokens=512,
     reference="https://huggingface.co/cointegrated/LaBSE-en-ru",
     similarity_fn_name=ScoringFunction.COSINE,
-    framework=["Sentence Transformers", "PyTorch"],
+    framework=["Sentence Transformers", "PyTorch", "Transformers", "safetensors"],
     use_instructions=False,
     public_training_code="https://colab.research.google.com/drive/1dnPRn0-ugj3vZgSpyCC9sgslM2SuSfHy?usp=sharing",
     public_training_data=None,
@@ -618,13 +629,14 @@ rubert_tiny_turbo = ModelMeta(
     revision="8ce0cf757446ce9bb2d5f5a4ac8103c7a1049054",
     release_date="2024-06-21",
     n_parameters=29_200_000,
+    n_embedding_parameters=26_154_336,
     memory_usage_mb=111,
     embed_dim=312,
     license="mit",
     max_tokens=2048,
     reference="https://huggingface.co/sergeyzh/rubert-tiny-turbo",
     similarity_fn_name=ScoringFunction.COSINE,
-    framework=["Sentence Transformers", "PyTorch"],
+    framework=["Sentence Transformers", "PyTorch", "safetensors", "Transformers"],
     use_instructions=False,
     public_training_code=None,
     public_training_data=None,
@@ -641,13 +653,14 @@ rubert_mini_frida = ModelMeta(
     revision="19b279b78afd945b5ccae78f63e284909814adc2",
     release_date="2025-03-02",
     n_parameters=32_300_000,
+    n_embedding_parameters=26_154_336,
     memory_usage_mb=123,
     embed_dim=312,
     license="mit",
     max_tokens=2048,
     reference="https://huggingface.co/sergeyzh/rubert-mini-frida",
     similarity_fn_name=ScoringFunction.COSINE,
-    framework=["Sentence Transformers", "PyTorch"],
+    framework=["Sentence Transformers", "PyTorch", "safetensors", "Transformers"],
     use_instructions=True,
     public_training_code=None,
     public_training_data=None,
@@ -669,13 +682,14 @@ labse_ru_turbo = ModelMeta(
     revision="1940b046c6b5e125df11722b899130329d0a46da",
     release_date="2024-06-27",
     n_parameters=129_000_000,
+    n_embedding_parameters=42_303_744,
     memory_usage_mb=490,
     embed_dim=768,
     license="mit",
     max_tokens=512,
     reference="https://huggingface.co/sergeyzh/LaBSE-ru-turbo",
     similarity_fn_name=ScoringFunction.COSINE,
-    framework=["Sentence Transformers", "PyTorch"],
+    framework=["Sentence Transformers", "PyTorch", "safetensors", "Transformers"],
     use_instructions=False,
     training_datasets=turbo_models_datasets,
     public_training_code=None,
@@ -720,6 +734,7 @@ rosberta_ru_en = ModelMeta(
     use_instructions=True,
     reference="https://huggingface.co/ai-forever/ru-en-RoSBERTa",
     n_parameters=404_000_000,
+    n_embedding_parameters=100_869_120,
     memory_usage_mb=1540,
     max_tokens=512,
     embed_dim=1024,
@@ -745,7 +760,7 @@ rosberta_ru_en = ModelMeta(
     },
     public_training_data=None,
     public_training_code=None,
-    framework=["Sentence Transformers", "PyTorch"],
+    framework=["Sentence Transformers", "PyTorch", "safetensors", "Transformers"],
     citation="""@misc{snegirev2024russianfocusedembeddersexplorationrumteb,
       title={The Russian-focused embedders' exploration: ruMTEB benchmark and Russian embedding model design},
       author={Artem Snegirev and Maria Tikhonova and Anna Maksimova and Alena Fenogenova and Alexander Abramov},
@@ -886,6 +901,7 @@ frida = ModelMeta(
     use_instructions=True,
     reference="https://huggingface.co/ai-forever/FRIDA",
     n_parameters=823_000_000,
+    n_embedding_parameters=143_847_936,
     memory_usage_mb=3141,
     max_tokens=512,
     embed_dim=1536,
@@ -895,7 +911,7 @@ frida = ModelMeta(
     training_datasets=frida_training_datasets,
     public_training_data=None,
     public_training_code=None,
-    framework=["Sentence Transformers", "PyTorch"],
+    framework=["Sentence Transformers", "PyTorch", "safetensors", "Transformers"],
     citation=None,
 )
 
@@ -918,13 +934,14 @@ giga_embeddings = ModelMeta(
     revision="0ad5b29bfecd806cecc9d66b927d828a736594dc",
     release_date="2025-09-23",
     n_parameters=3_227_176_961,
+    n_embedding_parameters=None,
     memory_usage_mb=12865,
     embed_dim=2048,
     license="mit",
     max_tokens=4096,
     reference="https://huggingface.co/ai-sage/Giga-Embeddings-instruct",
     similarity_fn_name=ScoringFunction.COSINE,
-    framework=["Sentence Transformers", "PyTorch"],
+    framework=["Sentence Transformers", "PyTorch", "safetensors", "Transformers"],
     use_instructions=True,
     public_training_code=None,
     public_training_data=None,
@@ -950,13 +967,14 @@ berta = ModelMeta(
     revision="914c8c8aed14042ed890fc2c662d5e9e66b2faa7",
     release_date="2025-03-10",
     n_parameters=128_000_000,
+    n_embedding_parameters=42_303_744,
     memory_usage_mb=489,
     embed_dim=768,
     license="mit",
     max_tokens=512,
     reference="https://huggingface.co/sergeyzh/BERTA",
     similarity_fn_name=ScoringFunction.COSINE,
-    framework=["Sentence Transformers", "PyTorch"],
+    framework=["Sentence Transformers", "PyTorch", "safetensors", "Transformers"],
     use_instructions=True,
     training_datasets=berta_training_datasets,
     public_training_code=None,
@@ -1025,6 +1043,7 @@ user2_small = ModelMeta(
     use_instructions=True,
     reference="https://huggingface.co/collections/deepvk/user2-6802650d7210f222ec60e05f",
     n_parameters=34_400_000,
+    n_embedding_parameters=None,
     memory_usage_mb=131,
     max_tokens=8192,
     embed_dim=384,
@@ -1034,7 +1053,7 @@ user2_small = ModelMeta(
     training_datasets=user2_training_data,
     public_training_data=None,
     public_training_code="https://github.com/BlessedTatonka/some_code/tree/2899f27d51efdf4217fc6453799ff197e9792f1e",
-    framework=["Sentence Transformers", "PyTorch"],
+    framework=["Sentence Transformers", "PyTorch", "safetensors"],
     citation="""@misc{deepvk2025user,
     title={USER2},
     author={Malashenko, Boris and Spirin, Egor and Sokolov Andrey},
@@ -1058,6 +1077,7 @@ user2_base = ModelMeta(
     use_instructions=True,
     reference="https://huggingface.co/collections/deepvk/user2-6802650d7210f222ec60e05f",
     n_parameters=149_000_000,
+    n_embedding_parameters=None,
     memory_usage_mb=568,
     max_tokens=8192,
     embed_dim=768,
@@ -1067,7 +1087,7 @@ user2_base = ModelMeta(
     training_datasets=user2_training_data,
     public_training_data=None,
     public_training_code="https://github.com/BlessedTatonka/some_code/tree/2899f27d51efdf4217fc6453799ff197e9792f1e",
-    framework=["Sentence Transformers", "PyTorch"],
+    framework=["Sentence Transformers", "PyTorch", "safetensors"],
     citation="""@misc{deepvk2025user,
     title={USER2},
     author={Malashenko, Boris and Spirin, Egor and Sokolov Andrey},

mteb/models/model_implementations/ruri_models.py

@@ -38,13 +38,14 @@ cl_nagoya_ruri_v3_30m = ModelMeta(
     revision="24899e5de370b56d179604a007c0d727bf144504",
     release_date="2025-04-07",
     n_parameters=36_705_536,
+    n_embedding_parameters=None,
     memory_usage_mb=140,
     embed_dim=256,
     license="apache-2.0",
     max_tokens=8192,
     reference="https://huggingface.co/cl-nagoya/ruri-v3-30m",
     similarity_fn_name="cosine",
-    framework=["PyTorch", "Sentence Transformers"],
+    framework=["PyTorch", "Sentence Transformers", "safetensors"],
     use_instructions=True,
     superseded_by=None,
     training_datasets={
@@ -69,13 +70,14 @@ cl_nagoya_ruri_v3_70m = ModelMeta(
     revision="07a8b0aba47d29d2ca21f89b915c1efe2c23d1cc",
     release_date="2025-04-09",
     n_parameters=36_705_536,
+    n_embedding_parameters=None,
     memory_usage_mb=140,
     embed_dim=256,
     license="apache-2.0",
     max_tokens=8192,
     reference="https://huggingface.co/cl-nagoya/ruri-v3-70m",
     similarity_fn_name="cosine",
-    framework=["PyTorch", "Sentence Transformers"],
+    framework=["PyTorch", "Sentence Transformers", "safetensors"],
     use_instructions=True,
     superseded_by=None,
     training_datasets={"MrTidyRetrieval", "MIRACLRetrieval"},
@@ -98,13 +100,14 @@ cl_nagoya_ruri_v3_130m = ModelMeta(
     revision="e3114c6ee10dbab8b4b235fbc6dcf9dd4d5ac1a6",
     release_date="2025-04-09",
     n_parameters=132_140_544,
+    n_embedding_parameters=None,
     memory_usage_mb=504,
     embed_dim=512,
     license="apache-2.0",
     max_tokens=8192,
     reference="https://huggingface.co/cl-nagoya/ruri-v3-130m",
     similarity_fn_name="cosine",
-    framework=["PyTorch", "Sentence Transformers"],
+    framework=["PyTorch", "Sentence Transformers", "safetensors"],
     use_instructions=True,
     superseded_by=None,
     training_datasets={"MrTidyRetrieval", "MIRACLRetrieval"},
@@ -127,13 +130,14 @@ cl_nagoya_ruri_v3_310m = ModelMeta(
     revision="18b60fb8c2b9df296fb4212bb7d23ef94e579cd3",
     release_date="2025-04-09",
     n_parameters=314_611_968,
+    n_embedding_parameters=None,
     memory_usage_mb=1200,
     embed_dim=768,
     license="apache-2.0",
     max_tokens=8192,
     reference="https://huggingface.co/cl-nagoya/ruri-v3-310m",
     similarity_fn_name="cosine",
-    framework=["PyTorch", "Sentence Transformers"],
+    framework=["PyTorch", "Sentence Transformers", "safetensors"],
     use_instructions=True,
     superseded_by=None,
     training_datasets={"MrTidyRetrieval", "MIRACLRetrieval"},
@@ -157,13 +161,14 @@ cl_nagoya_ruri_small_v2 = ModelMeta(
     revision="db18646e673b713cd0518a5bb0fefdce21e77cd9",
     release_date="2024-12-05",
     n_parameters=68_087_808,
+    n_embedding_parameters=25_165_824,
     memory_usage_mb=260,
     embed_dim=768,
     license="apache-2.0",
     max_tokens=512,
     reference="https://huggingface.co/cl-nagoya/ruri-small-v2",
     similarity_fn_name="cosine",
-    framework=["PyTorch", "Sentence Transformers"],
+    framework=["PyTorch", "Sentence Transformers", "safetensors"],
     use_instructions=True,
     adapted_from="line-corporation/line-distilbert-base-japanese",
     superseded_by=None,
@@ -186,13 +191,14 @@ cl_nagoya_ruri_base_v2 = ModelMeta(
     revision="8ce03882903668a01c83ca3b8111ac025a3bc734",
     release_date="2024-12-05",
     n_parameters=111_207_168,
+    n_embedding_parameters=25_165_824,
     memory_usage_mb=424,
     embed_dim=768,
     license="apache-2.0",
     max_tokens=512,
     reference="https://huggingface.co/cl-nagoya/ruri-base-v2",
     similarity_fn_name="cosine",
-    framework=["PyTorch", "Sentence Transformers"],
+    framework=["PyTorch", "Sentence Transformers", "safetensors"],
     use_instructions=True,
     adapted_from="tohoku-nlp/bert-base-japanese-v3",
     superseded_by=None,
@@ -215,13 +221,14 @@ cl_nagoya_ruri_large_v2 = ModelMeta(
     revision="42898ef34a5574977380ebf0dfd28cbfbd36438b",
     release_date="2024-12-06",
     n_parameters=337_441_792,
+    n_embedding_parameters=33_554_432,
     memory_usage_mb=1287,
     embed_dim=1024,
     license="apache-2.0",
     max_tokens=512,
     reference="https://huggingface.co/cl-nagoya/ruri-large-v2",
     similarity_fn_name="cosine",
-    framework=["PyTorch", "Sentence Transformers"],
+    framework=["PyTorch", "Sentence Transformers", "safetensors"],
     use_instructions=True,
     adapted_from="tohoku-nlp/bert-large-japanese-v2",
     superseded_by=None,
@@ -245,13 +252,14 @@ cl_nagoya_ruri_small_v1 = ModelMeta(
     revision="bc56ce90cd7a979f6eb199fc52dfe700bfd94bc3",
     release_date="2024-08-28",
     n_parameters=68_087_808,
+    n_embedding_parameters=25_165_824,
     memory_usage_mb=130,
     embed_dim=768,
     license="apache-2.0",
     max_tokens=512,
     reference="https://huggingface.co/cl-nagoya/ruri-small",
     similarity_fn_name="cosine",
-    framework=["PyTorch", "Sentence Transformers"],
+    framework=["PyTorch", "Sentence Transformers", "safetensors"],
     use_instructions=True,
     adapted_from="line-corporation/line-distilbert-base-japanese",
     superseded_by="cl-nagoya/ruri-small-v2",
@@ -274,13 +282,14 @@ cl_nagoya_ruri_base_v1 = ModelMeta(
     revision="1ae40b8b6c78518a499425086bab8fc16c2e4b0e",
     release_date="2024-08-28",
     n_parameters=111_207_168,
+    n_embedding_parameters=25_165_824,
     memory_usage_mb=212,
     embed_dim=768,
     license="apache-2.0",
     max_tokens=512,
     reference="https://huggingface.co/cl-nagoya/ruri-base",
     similarity_fn_name="cosine",
-    framework=["PyTorch", "Sentence Transformers"],
+    framework=["PyTorch", "Sentence Transformers", "safetensors"],
     use_instructions=True,
     adapted_from="tohoku-nlp/bert-base-japanese-v3",
     superseded_by="cl-nagoya/ruri-base-v2",
@@ -304,13 +313,14 @@ cl_nagoya_ruri_large_v1 = ModelMeta(
     revision="a011c39b13e8bc137ee13c6bc82191ece46c414c",
     release_date="2024-08-28",
     n_parameters=337_441_792,
+    n_embedding_parameters=33_554_432,
     memory_usage_mb=644,
     embed_dim=1024,
     license="apache-2.0",
     max_tokens=512,
     reference="https://huggingface.co/cl-nagoya/ruri-large",
     similarity_fn_name="cosine",
-    framework=["PyTorch", "Sentence Transformers"],
+    framework=["PyTorch", "Sentence Transformers", "safetensors"],
     use_instructions=True,
     adapted_from="tohoku-nlp/bert-large-japanese-v2",
     superseded_by="cl-nagoya/ruri-large-v2",

mteb/models/model_implementations/salesforce_models.py

@@ -1,12 +1,18 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
 from mteb.models.instruct_wrapper import (
     InstructSentenceTransformerModel,
     instruct_wrapper,
 )
 from mteb.models.model_meta import ModelMeta, ScoringFunction
-from mteb.types import PromptType
 
 from .e5_instruct import E5_MISTRAL_TRAINING_DATA
 
+if TYPE_CHECKING:
+    from mteb.types import PromptType
+
 
 def instruction_template(
     instruction: str, prompt_type: PromptType | None = None
@@ -52,13 +58,14 @@ SFR_Embedding_2_R = ModelMeta(
     revision="91762139d94ed4371a9fa31db5551272e0b83818",
     release_date="2024-06-14",  # initial commit of hf model.
     n_parameters=7_110_000_000,
+    n_embedding_parameters=None,
     memory_usage_mb=13563,
     embed_dim=4096,
     license="cc-by-nc-4.0",
     max_tokens=32768,
     reference="https://huggingface.co/Salesforce/SFR-Embedding-2_R",
     similarity_fn_name=ScoringFunction.COSINE,
-    framework=["Sentence Transformers", "PyTorch"],
+    framework=["Sentence Transformers", "PyTorch", "safetensors", "Transformers"],
     use_instructions=True,
     adapted_from="intfloat/e5-mistral-7b-instruct",
     public_training_code=None,
@@ -90,13 +97,14 @@ SFR_Embedding_Code_2B_R = ModelMeta(
     revision="c73d8631a005876ed5abde34db514b1fb6566973",
     release_date="2025-01-17",  # initial commit of hf model.
     n_parameters=2_610_000_000,
+    n_embedding_parameters=None,
     memory_usage_mb=4986,
     embed_dim=2304,
     license="cc-by-nc-4.0",
     max_tokens=8192,
     reference="https://huggingface.co/Salesforce/SFR-Embedding-Code-2B_R",
     similarity_fn_name=ScoringFunction.COSINE,
-    framework=["Sentence Transformers", "PyTorch"],
+    framework=["Sentence Transformers", "PyTorch", "safetensors", "Transformers"],
     use_instructions=True,
     adapted_from="google/gemma-2-2b-it",
     public_training_code=None,
@@ -128,13 +136,14 @@ SFR_Embedding_Mistral = ModelMeta(
     revision="938c560d1c236aa563b2dbdf084f28ab28bccb11",
     release_date="2024-01-24",  # initial commit of hf model.
     n_parameters=7_110_000_000,
+    n_embedding_parameters=None,
     memory_usage_mb=13563,
     embed_dim=4096,
     license="cc-by-nc-4.0",
     max_tokens=32768,
     reference="https://huggingface.co/Salesforce/SFR-Embedding-Mistral",
     similarity_fn_name=ScoringFunction.COSINE,
-    framework=["Sentence Transformers", "PyTorch"],
+    framework=["Sentence Transformers", "PyTorch", "safetensors", "Transformers"],
     use_instructions=True,
     public_training_code=None,
     public_training_data=None,

mteb/models/model_implementations/samilpwc_models.py

@@ -51,13 +51,14 @@ samilpwc_expr = ModelMeta(
     revision="33358978be40f36491045f9c2a359d38c3f50047",
     release_date="2025-08-12",
     n_parameters=560_000_000,
+    n_embedding_parameters=256_002_048,
     memory_usage_mb=2136,
     embed_dim=1024,
     license="apache-2.0",
     max_tokens=514,
     reference="https://huggingface.co/SamilPwC-AXNode-GenAI/PwC-Embedding_expr",
     similarity_fn_name="cosine",
-    framework=["Sentence Transformers", "PyTorch"],
+    framework=["Sentence Transformers", "PyTorch", "safetensors", "Transformers"],
     use_instructions=True,
     public_training_code=None,
     public_training_data=None,

mteb/models/model_implementations/sarashina_embedding_models.py

@@ -124,13 +124,14 @@ sbintuitions_sarashina_embedding_v2_1b = ModelMeta(
     revision="1f3408afaa7b617e3445d891310a9c26dd0c68a5",
     release_date="2025-07-30",
     n_parameters=1_224_038_144,
+    n_embedding_parameters=183_500_800,
     memory_usage_mb=4669,
     embed_dim=1792,
     license="https://huggingface.co/sbintuitions/sarashina-embedding-v2-1b/blob/main/LICENSE",
     max_tokens=8192,
     reference="https://huggingface.co/sbintuitions/sarashina-embedding-v2-1b",
     similarity_fn_name="cosine",
-    framework=["Sentence Transformers", "PyTorch"],
+    framework=["Sentence Transformers", "PyTorch", "safetensors", "Transformers"],
     use_instructions=True,
     adapted_from="sbintuitions/sarashina2.2-1b",
     superseded_by=None,
@@ -150,13 +151,14 @@ sbintuitions_sarashina_embedding_v1_1b = ModelMeta(
     revision="d060fcd8984075071e7fad81baff035cbb3b6c7e",
     release_date="2024-11-22",
     n_parameters=1_224_038_144,
+    n_embedding_parameters=183_500_800,
     memory_usage_mb=4669,
     embed_dim=1792,
     license="https://huggingface.co/sbintuitions/sarashina-embedding-v1-1b/blob/main/LICENSE",
     max_tokens=8192,
     reference="https://huggingface.co/sbintuitions/sarashina-embedding-v1-1b",
     similarity_fn_name="cosine",
-    framework=["Sentence Transformers", "PyTorch"],
+    framework=["Sentence Transformers", "PyTorch", "safetensors", "Transformers"],
     use_instructions=False,
     adapted_from="sbintuitions/sarashina2.1-1b",
     superseded_by="sbintuitions/sarashina-embedding-v2-1b",

mteb/models/model_implementations/searchmap_models.py

@@ -27,13 +27,14 @@ searchmap_preview = ModelMeta(
     use_instructions=True,
     release_date="2025-03-05",
     n_parameters=435_000_000,
+    n_embedding_parameters=None,
     memory_usage_mb=1660,
     embed_dim=4096,
     license="mit",
     max_tokens=8192,
     reference="https://huggingface.co/VPLabs/SearchMap_Preview",
     similarity_fn_name="cosine",
-    framework=["Sentence Transformers", "PyTorch"],
+    framework=["Sentence Transformers", "PyTorch", "Transformers", "safetensors"],
     public_training_code=None,
     public_training_data=None,
     training_datasets=None,

mteb/models/model_implementations/seed_1_6_embedding_models.py

@@ -13,16 +13,18 @@ import torch
 from torch.utils.data import DataLoader
 
 from mteb._requires_package import requires_package
-from mteb.abstasks.task_metadata import TaskMetadata
 from mteb.models.abs_encoder import AbsEncoder
 from mteb.models.model_implementations.bge_models import bge_chinese_training_data
 from mteb.models.model_implementations.nvidia_models import nvidia_training_datasets
 from mteb.models.model_meta import ModelMeta
-from mteb.types import Array, BatchedInput, PromptType
+from mteb.types import PromptType
 
 if TYPE_CHECKING:
     from PIL import Image
 
+    from mteb.abstasks.task_metadata import TaskMetadata
+    from mteb.types import Array, BatchedInput
+
 
 logger = logging.getLogger(__name__)
 
@@ -429,6 +431,7 @@ seed_embedding = ModelMeta(
     embed_dim=2048,
     open_weights=False,
     n_parameters=None,
+    n_embedding_parameters=None,
     memory_usage_mb=None,
     license=None,
     reference="https://seed1-6-embedding.github.io/",