mteb 2.3.8__py3-none-any.whl → 2.3.9__py3-none-any.whl

mteb/models/model_implementations/e5_models.py

@@ -5,108 +5,10 @@ from mteb.models.model_meta import (
 from mteb.models.sentence_transformer_wrapper import sentence_transformers_loader
 from mteb.types import PromptType
 
+from .facebookai import XLMR_LANGUAGES
+
 E5_PAPER_RELEASE_DATE = "2024-02-08"
-XLMR_LANGUAGES = [
-    "afr-Latn",
-    "amh-Latn",
-    "ara-Latn",
-    "asm-Latn",
-    "aze-Latn",
-    "bel-Latn",
-    "bul-Latn",
-    "ben-Latn",
-    "ben-Beng",
-    "bre-Latn",
-    "bos-Latn",
-    "cat-Latn",
-    "ces-Latn",
-    "cym-Latn",
-    "dan-Latn",
-    "deu-Latn",
-    "ell-Latn",
-    "eng-Latn",
-    "epo-Latn",
-    "spa-Latn",
-    "est-Latn",
-    "eus-Latn",
-    "fas-Latn",
-    "fin-Latn",
-    "fra-Latn",
-    "fry-Latn",
-    "gle-Latn",
-    "gla-Latn",
-    "glg-Latn",
-    "guj-Latn",
-    "hau-Latn",
-    "heb-Latn",
-    "hin-Latn",
-    "hin-Deva",
-    "hrv-Latn",
-    "hun-Latn",
-    "hye-Latn",
-    "ind-Latn",
-    "isl-Latn",
-    "ita-Latn",
-    "jpn-Latn",
-    "jav-Latn",
-    "kat-Latn",
-    "kaz-Latn",
-    "khm-Latn",
-    "kan-Latn",
-    "kor-Latn",
-    "kur-Latn",
-    "kir-Latn",
-    "lat-Latn",
-    "lao-Latn",
-    "lit-Latn",
-    "lav-Latn",
-    "mlg-Latn",
-    "mkd-Latn",
-    "mal-Latn",
-    "mon-Latn",
-    "mar-Latn",
-    "msa-Latn",
-    "mya-Latn",
-    "nep-Latn",
-    "nld-Latn",
-    "nob-Latn",
-    "orm-Latn",
-    "ori-Latn",
-    "pan-Latn",
-    "pol-Latn",
-    "pus-Latn",
-    "por-Latn",
-    "ron-Latn",
-    "rus-Latn",
-    "san-Latn",
-    "snd-Latn",
-    "sin-Latn",
-    "slk-Latn",
-    "slv-Latn",
-    "som-Latn",
-    "sqi-Latn",
-    "srp-Latn",
-    "sun-Latn",
-    "swe-Latn",
-    "swa-Latn",
-    "tam-Latn",
-    "tam-Taml",
-    "tel-Latn",
-    "tel-Telu",
-    "tha-Latn",
-    "tgl-Latn",
-    "tur-Latn",
-    "uig-Latn",
-    "ukr-Latn",
-    "urd-Latn",
-    "urd-Arab",
-    "uzb-Latn",
-    "vie-Latn",
-    "xho-Latn",
-    "yid-Latn",
-    "zho-Hant",
-    "zho-Hans",
-]
+
 
 MULTILINGUAL_E5_CITATION = """
 @article{wang2024multilingual,

mteb/models/model_implementations/facebookai.py

@@ -0,0 +1,147 @@
+from mteb.models import sentence_transformers_loader
+from mteb.models.model_meta import ModelMeta, ScoringFunction
+
+XLMR_LANGUAGES = [
+    "afr-Latn",
+    "amh-Latn",
+    "ara-Latn",
+    "asm-Latn",
+    "aze-Latn",
+    "bel-Latn",
+    "bul-Latn",
+    "ben-Latn",
+    "ben-Beng",
+    "bre-Latn",
+    "bos-Latn",
+    "cat-Latn",
+    "ces-Latn",
+    "cym-Latn",
+    "dan-Latn",
+    "deu-Latn",
+    "ell-Latn",
+    "eng-Latn",
+    "epo-Latn",
+    "spa-Latn",
+    "est-Latn",
+    "eus-Latn",
+    "fas-Latn",
+    "fin-Latn",
+    "fra-Latn",
+    "fry-Latn",
+    "gle-Latn",
+    "gla-Latn",
+    "glg-Latn",
+    "guj-Latn",
+    "hau-Latn",
+    "heb-Latn",
+    "hin-Latn",
+    "hin-Deva",
+    "hrv-Latn",
+    "hun-Latn",
+    "hye-Latn",
+    "ind-Latn",
+    "isl-Latn",
+    "ita-Latn",
+    "jpn-Latn",
+    "jav-Latn",
+    "kat-Latn",
+    "kaz-Latn",
+    "khm-Latn",
+    "kan-Latn",
+    "kor-Latn",
+    "kur-Latn",
+    "kir-Latn",
+    "lat-Latn",
+    "lao-Latn",
+    "lit-Latn",
+    "lav-Latn",
+    "mlg-Latn",
+    "mkd-Latn",
+    "mal-Latn",
+    "mon-Latn",
+    "mar-Latn",
+    "msa-Latn",
+    "mya-Latn",
+    "nep-Latn",
+    "nld-Latn",
+    "nob-Latn",
+    "orm-Latn",
+    "ori-Latn",
+    "pan-Latn",
+    "pol-Latn",
+    "pus-Latn",
+    "por-Latn",
+    "ron-Latn",
+    "rus-Latn",
+    "san-Latn",
+    "snd-Latn",
+    "sin-Latn",
+    "slk-Latn",
+    "slv-Latn",
+    "som-Latn",
+    "sqi-Latn",
+    "srp-Latn",
+    "sun-Latn",
+    "swe-Latn",
+    "swa-Latn",
+    "tam-Latn",
+    "tam-Taml",
+    "tel-Latn",
+    "tel-Telu",
+    "tha-Latn",
+    "tgl-Latn",
+    "tur-Latn",
+    "uig-Latn",
+    "ukr-Latn",
+    "urd-Latn",
+    "urd-Arab",
+    "uzb-Latn",
+    "vie-Latn",
+    "xho-Latn",
+    "yid-Latn",
+    "zho-Hant",
+    "zho-Hans",
+]
+
+
+xlmr_base = ModelMeta(
+    loader=sentence_transformers_loader,  # type: ignore[arg-type]
+    name="FacebookAI/xlm-roberta-base",
+    languages=XLMR_LANGUAGES,
+    open_weights=True,
+    revision="e73636d4f797dec63c3081bb6ed5c7b0bb3f2089",
+    release_date="2019-11-05",  # arxiv paper release
+    n_parameters=278043648,
+    memory_usage_mb=1064,
+    embed_dim=768,
+    license="mit",
+    max_tokens=512,
+    reference="https://huggingface.co/FacebookAI/xlm-roberta-base",
+    similarity_fn_name=ScoringFunction.COSINE,
+    framework=["Sentence Transformers", "PyTorch"],
+    use_instructions=False,
+    public_training_code=None,
+    public_training_data=None,
+    training_datasets=set(),
+)
+
+xlmr_large = ModelMeta(
+    loader=sentence_transformers_loader,  # type: ignore[arg-type]
+    name="FacebookAI/xlm-roberta-large",
+    languages=XLMR_LANGUAGES,
+    open_weights=True,
+    revision="c23d21b0620b635a76227c604d44e43a9f0ee389",
+    release_date="2019-11-05",  # arxiv paper release
+    n_parameters=559890432,
+    memory_usage_mb=2141,
+    embed_dim=1024,
+    license="mit",
+    max_tokens=512,
+    reference="https://huggingface.co/FacebookAI/xlm-roberta-large",
+    similarity_fn_name=ScoringFunction.COSINE,
+    framework=["Sentence Transformers", "PyTorch"],
+    use_instructions=False,
+    public_training_code=None,
+    public_training_data=None,
+    training_datasets=set(),
+)

mteb/models/model_implementations/kblab.py

@@ -0,0 +1,24 @@
+from mteb.models import sentence_transformers_loader
+from mteb.models.model_meta import ModelMeta, ScoringFunction
+
+sbert_swedish = ModelMeta(
+    loader=sentence_transformers_loader,  # type: ignore[arg-type]
+    name="KBLab/sentence-bert-swedish-cased",
+    languages=["swe-Latn"],
+    open_weights=True,
+    revision="6b5e83cd29c03729cfdc33d13b1423399b0efb5c",
+    release_date="2023-01-11",
+    n_parameters=124690944,
+    memory_usage_mb=476,
+    embed_dim=768,
+    license="apache-2.0",
+    max_tokens=384,
+    reference="https://huggingface.co/KBLab/sentence-bert-swedish-cased",
+    similarity_fn_name=ScoringFunction.COSINE,
+    framework=["Sentence Transformers", "PyTorch"],
+    use_instructions=False,
+    public_training_code=None,
+    public_training_data=None,
+    training_datasets=None,
+    adapted_from="sentence-transformers/all-mpnet-base-v2",
+)

mteb/models/model_implementations/kfst.py

@@ -0,0 +1,24 @@
+from mteb.models import sentence_transformers_loader
+from mteb.models.model_meta import ModelMeta, ScoringFunction
+
+xlmr_scandi = ModelMeta(
+    loader=sentence_transformers_loader,  # type: ignore[arg-type]
+    name="KFST/XLMRoberta-en-da-sv-nb",
+    languages=["swe-Latn", "nob-Latn", "nno-Latn", "dan-Latn", "eng-Latn"],
+    open_weights=True,
+    revision="d40c10ca7b1e68b5a8372f2d112dac9eb3279df1",
+    release_date="2022-02-22",
+    n_parameters=278043648,
+    memory_usage_mb=1061,
+    embed_dim=768,
+    license="not specified",
+    max_tokens=512,
+    reference="https://huggingface.co/KFST/XLMRoberta-en-da-sv-nb",
+    similarity_fn_name=ScoringFunction.COSINE,
+    framework=["Sentence Transformers", "PyTorch"],
+    use_instructions=False,
+    public_training_code=None,
+    public_training_data=None,
+    training_datasets=None,
+    adapted_from="FacebookAI/xlm-roberta-base",
+)

{mteb-2.3.8.dist-info → mteb-2.3.9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mteb
-Version: 2.3.8
+Version: 2.3.9
 Summary: Massive Text Embedding Benchmark
 Author-email: MTEB Contributors <niklas@huggingface.co>, Kenneth Enevoldsen <kenneth.enevoldsen@cas.au.dk>, Nouamane Tazi <nouamane@huggingface.co>, Nils Reimers <info@nils-reimers.de>
 Maintainer-email: Kenneth Enevoldsen <kenneth.enevoldsen@cas.au.dk>, Roman Solomatin <risolomatin@gmail.com>, Isaac Chung <chungisaac1217@gmail.com>

{mteb-2.3.8.dist-info → mteb-2.3.9.dist-info}/RECORD

@@ -1477,7 +1477,7 @@ mteb/models/model_implementations/colsmol_models.py,sha256=O2M7Ksydh94M_Iax4KytH
 mteb/models/model_implementations/conan_models.py,sha256=G-s7xo9VtNX-f7lWKtYVGHHiMMN0Xp44PlNIp7E0LAo,6502
 mteb/models/model_implementations/dino_models.py,sha256=QFgaFHR5YKrylqJGSljXCBn2W7qHhmF6KdXkvHrQNEI,16380
 mteb/models/model_implementations/e5_instruct.py,sha256=9R4GoSFicgqNDCh3HhTN_8L1qhzuEKvatjHYn3T9zlU,7676
-mteb/models/model_implementations/e5_models.py,sha256=vsqkmm6XzZn9ROj_OUR0j2KiN75MEuQsOPeoyc1AeYg,10937
+mteb/models/model_implementations/e5_models.py,sha256=ZLRgzx2uEBc_yWY6DwcJFUNKG6RHpWSEVp1_jaEURhs,9373
 mteb/models/model_implementations/e5_v.py,sha256=_9W7I0ryIzx_H9eCkzwdm8iHdGX1LIjKGXkhSh_zNv8,6690
 mteb/models/model_implementations/eagerworks_models.py,sha256=NOQkCUqn9jLSpf9p6KyaIHnJxYV1MNlr2z7hO2AcRSc,5744
 mteb/models/model_implementations/emillykkejensen_models.py,sha256=QdhGqCm_1-AURkrniZj2S1MjwwIVOPMzLvpgfJq-3EQ,2779
@@ -1485,6 +1485,7 @@ mteb/models/model_implementations/en_code_retriever.py,sha256=leZ-0M6LrunocY3XQB
 mteb/models/model_implementations/euler_models.py,sha256=fZoXYeDjSRN2Qj1Pf-ROi8xok03PjhYi4FLEZKjMPkk,905
 mteb/models/model_implementations/evaclip_models.py,sha256=cPMGYLDIq4s8zJxb4vPXqJ-rqwPaq7KOh2QZSO6cDas,8000
 mteb/models/model_implementations/fa_models.py,sha256=WGal70_ezITWoNdjcMdbOCTSCtoaXzuPadYstLVXxhg,7478
+mteb/models/model_implementations/facebookai.py,sha256=uhE6rB1YgxE0SIc7u8heE1U62qRFFA23IMgpjxBq_Ok,3116
 mteb/models/model_implementations/geogpt_models.py,sha256=Juv86SwhgQX80lVLjAFtim2aSiJT1AcgjniyyiKyk1Q,1923
 mteb/models/model_implementations/gme_v_models.py,sha256=NkfgR3_UdZzoBt1NnalVou6LOR-F7qXM4by9EbAVrys,13568
 mteb/models/model_implementations/google_models.py,sha256=7QfsaJ5JNDRQxFl7Zh2AtiR2PR7PZcfeCBgviuOFBCo,9130
@@ -1499,7 +1500,9 @@ mteb/models/model_implementations/jasper_models.py,sha256=ZY7qRRpBpD3eVryQb4rLs5
 mteb/models/model_implementations/jina_clip.py,sha256=CfiIxbhKspjQajNtObCfGPHOWPk6uLn4cuwydQHFTMo,5118
 mteb/models/model_implementations/jina_models.py,sha256=HrHm2Io3g9gHwxU5icAaudy_E8rAVkAAIFSzVYWF-dM,34859
 mteb/models/model_implementations/kalm_models.py,sha256=FmW7Z5Qs6WYBLuKvql3u4IJW36kj4k-Ypah8qTBEBkg,59837
+mteb/models/model_implementations/kblab.py,sha256=DDh8gDEI6YPjS4_yGYWC4HatE0mFf7vhGDU83zzV7V0,866
 mteb/models/model_implementations/kennethenevoldsen_models.py,sha256=DF-9nmsewYO9ikZ0kV81ujKGr7Ot36-9iPoxN7KX2mY,2993
+mteb/models/model_implementations/kfst.py,sha256=BQj0fxMJwyA6NOdK26NDYVL3z2PW1_F-lTTVImxEWZQ,892
 mteb/models/model_implementations/kowshik24_models.py,sha256=HoQpybjhquK2XSnawlq0aiSWFI5M7l6N4DNY4MQ-P10,976
 mteb/models/model_implementations/lens_models.py,sha256=fC7_NB1F8vBAlXD0p0-hALf6eZTPFJwpz57dy71OlwI,1696
 mteb/models/model_implementations/lgai_embedding_models.py,sha256=S83pbfkMH3YUNl4skusgbK-Rn-uLuScQVxgXwegR_N4,2333
@@ -2578,9 +2581,9 @@ mteb/types/_metadata.py,sha256=NN-W0S6a5TDV7UkpRx1pyWtGF4TyyCyoPUfHOwdeci8,2290
 mteb/types/_result.py,sha256=CRAUc5IvqI3_9SyXDwv-PWLCXwXdZem9RePeYESRtuw,996
 mteb/types/_string_validators.py,sha256=PY-dYq4E8O50VS3bLYdldPWp400fl_WzUjfVSkNWe8U,523
 mteb/types/statistics.py,sha256=YwJsxTf1eaCI_RE-J37a-gK5wDeGAsmkeZKoZCFihSo,3755
-mteb-2.3.8.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-mteb-2.3.8.dist-info/METADATA,sha256=QMpRmhMLXi45L0d29kCoNcEugCwDl8IWCc3wE_r-fb4,13923
-mteb-2.3.8.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-mteb-2.3.8.dist-info/entry_points.txt,sha256=8IJoEJFKoDHmVnNev-qJ9pp4Ln7_1-ma9QsXnzVCzGU,39
-mteb-2.3.8.dist-info/top_level.txt,sha256=OLVIjcQAlWBz0bdmutKlWHLF42FF0hp4uVAg3ZyiG4U,5
-mteb-2.3.8.dist-info/RECORD,,
+mteb-2.3.9.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+mteb-2.3.9.dist-info/METADATA,sha256=da_FgK7mGK2HivEwQfKDyIPYzDVMFaz-lTeVQVvp2q8,13923
+mteb-2.3.9.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+mteb-2.3.9.dist-info/entry_points.txt,sha256=8IJoEJFKoDHmVnNev-qJ9pp4Ln7_1-ma9QsXnzVCzGU,39
+mteb-2.3.9.dist-info/top_level.txt,sha256=OLVIjcQAlWBz0bdmutKlWHLF42FF0hp4uVAg3ZyiG4U,5
+mteb-2.3.9.dist-info/RECORD,,