mteb 2.1.4__py3-none-any.whl → 2.1.5__py3-none-any.whl

mteb/models/model_implementations/tarka_models.py

@@ -0,0 +1,58 @@
+from mteb.models.model_implementations.google_models import gemma_embedding_loader
+from mteb.models.model_meta import ModelMeta
+
+Tarka_Embedding_150M_V1_CITATION = """@misc{tarka_ai_research_2025,
+	author       = { Tarka AI Research },
+	title        = { Tarka-Embedding-150M-V1 (Revision c5f4f43) },
+	year         = 2025,
+	url          = { https://huggingface.co/Tarka-AIR/Tarka-Embedding-150M-V1 },
+	doi          = { 10.57967/hf/6875 },
+	publisher    = { Hugging Face }
+}"""
+
+MULTILINGUAL_EVALUATED_LANGUAGES = [
+    "arb-Arab",
+    "eng-Latn",
+    "spa-Latn",
+    "deu-Latn",
+    "fra-Latn",
+    "jpn-Jpan",
+    "kor-Hang",
+    "zho-Hans",
+]
+
+training_data = {
+    "T2Retrieval",
+    "DuRetrieval",
+    "MMarcoReranking",
+    "CMedQAv2-reranking",
+    "NQ",
+    "MSMARCO",
+    "HotpotQA",
+    "FEVER",
+    "MrTidyRetrieval",
+    "MIRACLRetrieval",
+    "CodeSearchNet",
+}
+
+tarka_embedding_150m_v1 = ModelMeta(
+    loader=gemma_embedding_loader,
+    name="Tarka-AIR/Tarka-Embedding-150M-V1",
+    languages=MULTILINGUAL_EVALUATED_LANGUAGES,
+    open_weights=True,
+    revision="c5f4f43",
+    release_date="2025-11-04",
+    n_parameters=155_714_304,
+    embed_dim=768,
+    max_tokens=2048,
+    license="gemma",
+    reference="https://huggingface.co/Tarka-AIR/Tarka-Embedding-150M-V1",
+    framework=["Sentence Transformers", "PyTorch"],
+    use_instructions=True,
+    public_training_code=None,
+    public_training_data=None,
+    training_datasets=training_data,
+    similarity_fn_name="cosine",
+    memory_usage_mb=576,
+    citation=Tarka_Embedding_150M_V1_CITATION,
+)

mteb/models/search_wrappers.py

@@ -191,6 +191,7 @@ class SearchEncoderWrapper:
             cos_scores_top_k_idx = cos_scores_top_k_idx.cpu().tolist()
             cos_scores_top_k_values = cos_scores_top_k_values.cpu().tolist()
 
+            sub_corpus_ids = list(sub_corpus_ids)
             for query_itr in range(len(query_embeddings)):
                 query_id = query_idx_to_id[query_itr]
                 for sub_corpus_id, score in zip(

{mteb-2.1.4.dist-info → mteb-2.1.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mteb
-Version: 2.1.4
+Version: 2.1.5
 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-2.1.4.dist-info → mteb-2.1.5.dist-info}/RECORD

@@ -1419,7 +1419,7 @@ mteb/models/get_model_meta.py,sha256=VpZZNINk-QrNeVpPZnlqzlLhtBs8G84eRwTzAb_gRD4
 mteb/models/instruct_wrapper.py,sha256=HxHmnlxkjtZhfgTZRYJBT3Nma7Dhx6a9e2Bg-cO_IYs,8844
 mteb/models/model_meta.py,sha256=b-Nel9nX5bJk4cgJnqkBzEKyMY7uXvxlCBSxmmH1Ios,14769
 mteb/models/models_protocols.py,sha256=D2hYWn_UBGMaKtRwBx3u0B0ni6lHJjSzTxX21XFNwIc,8917
-mteb/models/search_wrappers.py,sha256=0McxwGnqyiYKPHjHsxWZp1pP9qGuHemZjeX1z5ZgNAI,15588
+mteb/models/search_wrappers.py,sha256=W99EeMDQ58N0auVp2-7T39orG7GZLekSsVCdxEZLxw0,15638
 mteb/models/sentence_transformer_wrapper.py,sha256=n5CMsM6Lpg_CFHH0NkpJusMsaLUTt-L9vRmFINQ961k,12338
 mteb/models/cache_wrappers/__init__.py,sha256=j3JBHN73Tr7uMUO92FEvKXstnybxrPpGWmKXU2lAoIE,88
 mteb/models/cache_wrappers/cache_backend_protocol.py,sha256=TR7kD7KbN1J4piszIecpegtLZYGy7sRHZt3SDWlImKk,1665
@@ -1521,6 +1521,7 @@ mteb/models/model_implementations/shuu_model.py,sha256=KkcuVYjIzoha3Fvxh8ppqHQ9B
 mteb/models/model_implementations/siglip_models.py,sha256=tvi8QB2ayBoeXsxwHrl5RFlkknvE6FM9N06zSBWGQD0,12602
 mteb/models/model_implementations/sonar_models.py,sha256=Nc6kAJRWSrxA57DPRrgOPHqS1dNhz2vsE_1ZA2JtigQ,4784
 mteb/models/model_implementations/stella_models.py,sha256=NL3tk-rnuBdznsQ-nmelqun4tFO2xKoNPPOOVKqnPGU,8062
+mteb/models/model_implementations/tarka_models.py,sha256=aj4PvEzZ6ZSKcvwYVuTxf1IFOvH4rmJHtbPUcRw1fMI,1568
 mteb/models/model_implementations/text2vec_models.py,sha256=zaHWRc2W0RYZAOetinqRzug9UGW0HmY5U-jYsLXA8wo,4160
 mteb/models/model_implementations/ua_sentence_models.py,sha256=fcvXR4-Rrt-UDTlDkh2ZAO1gO_ufCOHiT6EhoeKiHx8,1224
 mteb/models/model_implementations/uae_models.py,sha256=KZxH5a3t-sfh33xUBkLizEuyFAyPlGfnRsn-S7mjq74,3112
@@ -2536,9 +2537,9 @@ 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-2.1.4.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-mteb-2.1.4.dist-info/METADATA,sha256=3HJ0LwqN5B9zLnqA4j5PsmVknk75iAHG-qwtZqJdKW0,13573
-mteb-2.1.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-mteb-2.1.4.dist-info/entry_points.txt,sha256=8IJoEJFKoDHmVnNev-qJ9pp4Ln7_1-ma9QsXnzVCzGU,39
-mteb-2.1.4.dist-info/top_level.txt,sha256=OLVIjcQAlWBz0bdmutKlWHLF42FF0hp4uVAg3ZyiG4U,5
-mteb-2.1.4.dist-info/RECORD,,
+mteb-2.1.5.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+mteb-2.1.5.dist-info/METADATA,sha256=VunL5iKfFZLfKB-4Yruzd5vq31mhfNOT0JVjs2GibSQ,13573
+mteb-2.1.5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+mteb-2.1.5.dist-info/entry_points.txt,sha256=8IJoEJFKoDHmVnNev-qJ9pp4Ln7_1-ma9QsXnzVCzGU,39
+mteb-2.1.5.dist-info/top_level.txt,sha256=OLVIjcQAlWBz0bdmutKlWHLF42FF0hp4uVAg3ZyiG4U,5
+mteb-2.1.5.dist-info/RECORD,,