metadata
tags:
- mteb
model-index:
- name: student
results:
- task:
type: STS
dataset:
type: C-MTEB/AFQMC
name: MTEB AFQMC
config: default
split: validation
revision: None
metrics:
- type: cos_sim_pearson
value: 42.01013972878128
- type: cos_sim_spearman
value: 43.4493974759166
- type: euclidean_pearson
value: 41.9332741602486
- type: euclidean_spearman
value: 43.4565546063627
- type: manhattan_pearson
value: 41.9297043571561
- type: manhattan_spearman
value: 43.44509515848548
- task:
type: STS
dataset:
type: C-MTEB/ATEC
name: MTEB ATEC
config: default
split: test
revision: None
metrics:
- type: cos_sim_pearson
value: 47.48357848831134
- type: cos_sim_spearman
value: 48.0096502737997
- task:
type: STS
dataset:
type: mteb/biosses-sts
name: MTEB BIOSSES
config: default
split: test
revision: d3fb88f8f02e40887cd149695127462bbcf29b4a
metrics:
- type: cos_sim_pearson
value: 70.06631340065852
- type: cos_sim_spearman
value: 70.56425845690775
- task:
type: STS
dataset:
type: C-MTEB/BQ
name: MTEB BQ
config: default
split: test
revision: None
metrics:
- type: cos_sim_pearson
value: 63.30619967351764
- type: cos_sim_spearman
value: 65.57791727146774
- type: euclidean_pearson
value: 64.41653053459552
- type: euclidean_spearman
value: 65.60244311139472
- type: manhattan_pearson
value: 64.37518298990945
- type: manhattan_spearman
value: 65.56983205786409
- task:
type: BitextMining
dataset:
type: mteb/bucc-bitext-mining
name: MTEB BUCC (zh-en)
config: zh-en
split: test
revision: d51519689f32196a32af33b075a01d0e7c51e252
metrics:
- type: accuracy
value: 98.42022116903634
- type: f1
value: 98.38511497279269
- type: precision
value: 98.36756187467088
- type: recall
value: 98.42022116903634
- task:
type: STS
dataset:
type: C-MTEB/LCQMC
name: MTEB LCQMC
config: default
split: test
revision: None
metrics:
- type: cos_sim_pearson
value: 71.3095132213625
- type: cos_sim_spearman
value: 75.55615792829865
- type: euclidean_pearson
value: 74.37147909656647
- type: euclidean_spearman
value: 75.54784459711308
- type: manhattan_pearson
value: 74.29759624788565
- type: manhattan_spearman
value: 75.49037321257157
- task:
type: STS
dataset:
type: C-MTEB/PAWSX
name: MTEB PAWSX
config: default
split: test
revision: None
metrics:
- type: cos_sim_pearson
value: 42.821882144591406
- type: cos_sim_spearman
value: 47.616725737501724
- type: euclidean_pearson
value: 46.991556480777675
- type: euclidean_spearman
value: 47.624128831089685
- type: manhattan_pearson
value: 46.83451589707148
- type: manhattan_spearman
value: 47.47345373932411
- task:
type: STS
dataset:
type: C-MTEB/QBQTC
name: MTEB QBQTC
config: default
split: test
revision: None
metrics:
- type: cos_sim_pearson
value: 39.48274306266568
- type: cos_sim_spearman
value: 40.43254828668596
- type: euclidean_pearson
value: 39.121198397707374
- type: euclidean_spearman
value: 40.47848829374869
- type: manhattan_pearson
value: 39.07044184765326
- type: manhattan_spearman
value: 40.41344728276686
- task:
type: STS
dataset:
type: mteb/sickr-sts
name: MTEB SICK-R
config: default
split: test
revision: a6ea5a8cab320b040a23452cc28066d9beae2cee
metrics:
- type: cos_sim_pearson
value: 81.60488630930521
- type: cos_sim_spearman
value: 79.04311658059933
- type: euclidean_pearson
value: 78.95158745413384
- type: euclidean_spearman
value: 78.99206332696008
- type: manhattan_pearson
value: 78.93956396383128
- type: manhattan_spearman
value: 78.94138617747835
- task:
type: STS
dataset:
type: mteb/sts12-sts
name: MTEB STS12
config: default
split: test
revision: a0d554a64d88156834ff5ae9920b964011b16384
metrics:
- type: cos_sim_pearson
value: 85.50516203958485
- type: cos_sim_spearman
value: 78.39314964894021
- type: euclidean_pearson
value: 83.03876157406377
- type: euclidean_spearman
value: 78.43128279495177
- type: manhattan_pearson
value: 83.00734833664097
- type: manhattan_spearman
value: 78.33755694741544
- task:
type: STS
dataset:
type: mteb/sts13-sts
name: MTEB STS13
config: default
split: test
revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca
metrics:
- type: cos_sim_pearson
value: 82.52249245791886
- type: cos_sim_spearman
value: 83.71503684399218
- type: euclidean_pearson
value: 82.83033355582003
- type: euclidean_spearman
value: 83.6956570069731
- type: manhattan_pearson
value: 82.74415910929217
- type: manhattan_spearman
value: 83.58167243171766
- task:
type: STS
dataset:
type: mteb/sts14-sts
name: MTEB STS14
config: default
split: test
revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375
metrics:
- type: cos_sim_pearson
value: 81.00915974657362
- type: cos_sim_spearman
value: 79.19276300509559
- type: euclidean_pearson
value: 80.17657754340593
- type: euclidean_spearman
value: 79.19425018312683
- type: manhattan_pearson
value: 80.04321829436775
- type: manhattan_spearman
value: 79.0458687679498
- task:
type: STS
dataset:
type: mteb/sts15-sts
name: MTEB STS15
config: default
split: test
revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3
metrics:
- type: cos_sim_pearson
value: 84.99452083625762
- type: cos_sim_spearman
value: 85.57952966879047
- type: euclidean_pearson
value: 85.14932626009531
- type: euclidean_spearman
value: 85.59697259700918
- type: manhattan_pearson
value: 85.11214415799934
- type: manhattan_spearman
value: 85.54871088485925
- task:
type: STS
dataset:
type: mteb/sts16-sts
name: MTEB STS16
config: default
split: test
revision: 4d8694f8f0e0100860b497b999b3dbed754a0513
metrics:
- type: cos_sim_pearson
value: 80.33170312674788
- type: cos_sim_spearman
value: 82.3316942254394
- type: euclidean_pearson
value: 82.00948134099386
- type: euclidean_spearman
value: 82.32475375375705
- type: manhattan_pearson
value: 81.94953036676401
- type: manhattan_spearman
value: 82.26329177825353
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (en-en)
config: en-en
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 87.60426458021554
- type: cos_sim_spearman
value: 87.89776827373123
- type: euclidean_pearson
value: 88.19401282603557
- type: euclidean_spearman
value: 87.90080500648473
- type: manhattan_pearson
value: 88.39099772653003
- type: manhattan_spearman
value: 88.03019288557621
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (en)
config: en
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 60.38925903960008
- type: cos_sim_spearman
value: 63.91952542589123
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (zh)
config: zh
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 61.51076949065575
- type: cos_sim_spearman
value: 67.24427398434739
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (zh-en)
config: zh-en
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 70.08946142653247
- type: cos_sim_spearman
value: 70.01280058113731
- task:
type: STS
dataset:
type: C-MTEB/STSB
name: MTEB STSB
config: default
split: test
revision: None
metrics:
- type: cos_sim_pearson
value: 75.52896222293855
- type: cos_sim_spearman
value: 75.38140772041567
- task:
type: STS
dataset:
type: mteb/stsbenchmark-sts
name: MTEB STSBenchmark
config: default
split: test
revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831
metrics:
- type: cos_sim_pearson
value: 85.09649790270096
- type: cos_sim_spearman
value: 85.99053080606336
- type: euclidean_pearson
value: 85.9554143396231
- type: euclidean_spearman
value: 85.9826211701156
- type: manhattan_pearson
value: 85.91951912635923
- type: manhattan_spearman
value: 85.90751385480418
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (cmn-eng)
config: cmn-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96.3
- type: f1
value: 95.15
- type: precision
value: 94.58333333333333
- type: recall
value: 96.3
Use Chinese and English STS and NLI corpora to conduct contrastive learning finetuning on xlmr
Using HuggingFace Transformers
from transformers import AutoTokenizer, AutoModel
import torch
# Sentences we want sentence embeddings for
sentences = ["样例数据-1", "样例数据-2"]
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('zhou-xl/bi-cse')
model = AutoModel.from_pretrained('zhou-xl/bi-cse')
model.eval()
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, cls pooling.
sentence_embeddings = model_output[0][:, 0]
# normalize embeddings
sentence_embeddings = torch.nn.functional.normalize(sentence_embeddings, p=2, dim=1)
print("Sentence embeddings:", sentence_embeddings)