Measuring Embeddings V4.2
這是一個在測量領域數據集上微調的句子轉換器模型,用於生成語義嵌入向量,支持語義文本相似性、語義搜索等任務。
下載量 61
發布時間 : 3/12/2025
模型概述
該模型基於intfloat/multilingual-e5-large-instruct微調,專門用於處理測量工程領域的文本,將句子和段落映射到1024維密集向量空間。
模型特點
測量領域優化
在measuring-embeddings-v4數據集上微調,特別適合處理測量工程領域的專業術語和概念
高維語義空間
將文本映射到1024維密集向量空間,能捕捉細微的語義差異
多語言支持
基於multilingual-e5-large-instruct基礎模型,具備多語言處理能力
長文本處理
支持最大512個標記的序列長度,能處理較長的專業描述文本
模型能力
語義文本相似性計算
語義搜索
文本分類
聚類分析
複述挖掘
使用案例
測量工程
校準記錄匹配
自動匹配和關聯設備校準記錄與相關技術文檔
提高校準文檔管理的效率和準確性
技術文檔檢索
基於語義相似性的測量系統技術文檔檢索
幫助工程師快速找到相關技術資料
質量控制
不確定度分析
關聯不確定度點數據與相關測量系統文檔
支持更全面的不確定度評估流程
🚀 基於intfloat/multilingual-e5-large-instruct的句子轉換器模型
本模型是基於 sentence-transformers 框架,在 measuring-embeddings-v4 數據集上對 intfloat/multilingual-e5-large-instruct 模型進行微調得到的。它可以將句子和段落映射到一個 1024 維的密集向量空間,可用於語義文本相似度計算、語義搜索、釋義挖掘、文本分類、聚類等任務。
🚀 快速開始
首先,你需要安裝 sentence-transformers
庫:
pip install -U sentence-transformers
然後,你可以加載該模型並進行推理:
from sentence_transformers import SentenceTransformer
# 從 🤗 Hub 下載模型
model = SentenceTransformer("Lauther/measuring-embeddings-v4.2")
# 進行推理
sentences = [
'uncertainty points',
'What is a Fluid?\nA Fluid is the substance measured within a measurement system. It can be a gas or liquid, such as hydrocarbons, water, or other industrial fluids. Proper classification of fluids is essential for ensuring measurement accuracy, regulatory compliance, and operational efficiency. By identifying fluids correctly, the system applies the appropriate measurement techniques, processing methods, and reporting standards.',
'What is a Calibration Point?\nA Calibration Point represents a specific data entry in a calibration process, comparing an expected reference value to an actual measured value. These points are fundamental in ensuring measurement accuracy and identifying deviations.\n\nKey Aspects of Calibration Points:\n- Calibration Report Association: Each calibration point belongs to a specific calibration report, linking it to a broader calibration procedure.\n- Reference Values: Theoretical or expected values used as a benchmark for measurement validation.\n- Measured Values: The actual recorded values during calibration, reflecting the instrument’s response.\n- Errors: The difference between reference and measured values, indicating possible measurement inaccuracies.\nCalibration points are essential for evaluating instrument performance, ensuring compliance with standards, and maintaining measurement reliability.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]
# 獲取嵌入向量的相似度分數
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
✨ 主要特性
- 多用途:可用於語義文本相似度計算、語義搜索、釋義挖掘、文本分類、聚類等多種自然語言處理任務。
- 高維向量空間:能夠將句子和段落映射到 1024 維的密集向量空間,有效捕捉語義信息。
- 微調模型:基於
intfloat/multilingual-e5-large-instruct
模型在特定數據集上進行微調,更適用於特定領域的任務。
📦 安裝指南
安裝 sentence-transformers
庫:
pip install -U sentence-transformers
💻 使用示例
基礎用法
from sentence_transformers import SentenceTransformer
# 從 🤗 Hub 下載模型
model = SentenceTransformer("Lauther/measuring-embeddings-v4.2")
# 進行推理
sentences = [
'uncertainty points',
'What is a Fluid?\nA Fluid is the substance measured within a measurement system. It can be a gas or liquid, such as hydrocarbons, water, or other industrial fluids. Proper classification of fluids is essential for ensuring measurement accuracy, regulatory compliance, and operational efficiency. By identifying fluids correctly, the system applies the appropriate measurement techniques, processing methods, and reporting standards.',
'What is a Calibration Point?\nA Calibration Point represents a specific data entry in a calibration process, comparing an expected reference value to an actual measured value. These points are fundamental in ensuring measurement accuracy and identifying deviations.\n\nKey Aspects of Calibration Points:\n- Calibration Report Association: Each calibration point belongs to a specific calibration report, linking it to a broader calibration procedure.\n- Reference Values: Theoretical or expected values used as a benchmark for measurement validation.\n- Measured Values: The actual recorded values during calibration, reflecting the instrument’s response.\n- Errors: The difference between reference and measured values, indicating possible measurement inaccuracies.\nCalibration points are essential for evaluating instrument performance, ensuring compliance with standards, and maintaining measurement reliability.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]
# 獲取嵌入向量的相似度分數
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
📚 詳細文檔
模型詳情
模型描述
屬性 | 詳情 |
---|---|
模型類型 | 句子轉換器 |
基礎模型 | intfloat/multilingual-e5-large-instruct |
最大序列長度 | 512 個標記 |
輸出維度 | 1024 維 |
相似度函數 | 餘弦相似度 |
訓練數據集 | measuring-embeddings-v4 |
模型來源
- 文檔:Sentence Transformers 文檔
- 倉庫:GitHub 上的 Sentence Transformers
- Hugging Face:Hugging Face 上的 Sentence Transformers
完整模型架構
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
(1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
(2): Normalize()
)
訓練詳情
訓練數據集
measuring-embeddings-v4
- 數據集:measuring-embeddings-v4,版本為 1e3ca2c
- 大小:3075 個訓練樣本
- 列:
sentence1
、sentence2
和score
- 基於前 1000 個樣本的近似統計信息:
| | sentence1 | sentence2 | score |
| ---- | ---- | ---- | ---- |
| 類型 | 字符串 | 字符串 | 浮點數 |
| 詳情 |
- 最小:3 個標記
- 平均:7.55 個標記
- 最大:17 個標記
- 最小:80 個標記
- 平均:180.22 個標記
- 最大:406 個標記
- 最小:0.07
- 平均:0.21
- 最大:0.95
- 樣本:
| sentence1 | sentence2 | score |
| ---- | ---- | ---- |
|
last calibrated span
|What are historical report values?<br>These represent the recorded data points within flow computer reports. Unlike the report index, which serves as a reference to locate reports, these values contain the actual measurements and calculated data stored in the historical records.<br><br>Flow computer reports store two types of data values:<br><br>- **Hourly data values**: Contain measured or calculated values (e.g., operational minutes, alarms set, etc.) recorded on an hourly basis.<br>- **Daily data values**: Contain measured or calculated values (e.g., operational minutes, alarms set, etc.) recorded on a daily basis.<br>Each value is directly linked to its respective report index, ensuring traceability to the original flow computer record. These values maintain their raw integrity, providing a reliable source for analysis and validation.
|0.1
| |flow computer configuration
|What is a Measurement Type?<br>Measurement types define the classification of measurements used within a system based on their purpose and regulatory requirements. These types include **fiscal**, **appropriation**, **operational**, and **custody** measurements. <br><br>- **Fiscal measurements** are used for tax and regulatory reporting, ensuring accurate financial transactions based on measured quantities. <br>- **Appropriation measurements** track resource allocation and ownership distribution among stakeholders. <br>- **Operational measurements** support real-time monitoring and process optimization within industrial operations. <br>- **Custody measurements** are essential for legal and contractual transactions, ensuring precise handover of fluids between parties. <br><br>These classifications play a crucial role in compliance, financial accuracy, and operational efficiency across industries such as oil and gas, water management, and energy distribution.
|0.1
| |uncertainty certificate number
|What is an Uncertainty Composition?<br>An Uncertainty Composition represents a specific factor that contributes to the overall uncertainty of a measurement system. These components are essential for evaluating the accuracy and reliability of measurements by identifying and quantifying the sources of uncertainty.<br><br>Key Aspects of an Uncertainty Component:<br>- Component Name: Defines the uncertainty factor (e.g., diameter, density, variance, covariance) influencing the measurement system.<br>- Value of Composition: Quantifies the component’s contribution to the total uncertainty, helping to analyze which factors have the greatest impact.<br>- Uncertainty File ID: Links the component to a specific uncertainty dataset for traceability and validation.<br>Understanding these components is critical for uncertainty analysis, ensuring compliance with industry standards and improving measurement precision.
|0.1
| - 損失函數:
CoSENTLoss
,參數如下:
{
"scale": 20.0,
"similarity_fct": "pairwise_cos_sim"
}
評估數據集
measuring-embeddings-v4
- 數據集:measuring-embeddings-v4,版本為 1e3ca2c
- 大小:659 個評估樣本
- 列:
sentence1
、sentence2
和score
- 基於前 659 個樣本的近似統計信息:
| | sentence1 | sentence2 | score |
| ---- | ---- | ---- | ---- |
| 類型 | 字符串 | 字符串 | 浮點數 |
| 詳情 |
- 最小:3 個標記
- 平均:7.63 個標記
- 最大:17 個標記
- 最小:80 個標記
- 平均:186.36 個標記
- 最大:406 個標記
- 最小:0.07
- 平均:0.2
- 最大:0.9
- 樣本:
| sentence1 | sentence2 | score |
| ---- | ---- | ---- |
|
measurement system details
|What is an Uncertainty Composition?<br>An Uncertainty Composition represents a specific factor that contributes to the overall uncertainty of a measurement system. These components are essential for evaluating the accuracy and reliability of measurements by identifying and quantifying the sources of uncertainty.<br><br>Key Aspects of an Uncertainty Component:<br>- Component Name: Defines the uncertainty factor (e.g., diameter, density, variance, covariance) influencing the measurement system.<br>- Value of Composition: Quantifies the component’s contribution to the total uncertainty, helping to analyze which factors have the greatest impact.<br>- Uncertainty File ID: Links the component to a specific uncertainty dataset for traceability and validation.<br>Understanding these components is critical for uncertainty analysis, ensuring compliance with industry standards and improving measurement precision.
|0.15
| |measurement system tag EMED-3102-02-010
|What is a report index or historic index?<br>Indexes represent the recorded reports generated by flow computers, classified into two types: <br>- **Hourly reports Index**: Store data for hourly events.<br>- **Daily reports Index**: Strore data for daily events.<br><br>These reports, also referred to as historical data or flow computer historical records, contain raw, first-hand measurements directly collected from the flow computer. The data has not been processed or used in any calculations, preserving its original state for analysis or validation.<br><br>The index is essential for locating specific values within the report.
|0.24
| |static pressure
|What is a Meter Stream?<br>A Meter Stream represents a measurement system configured within a flow computer. It serves as the interface between the physical measurement system and the computational processes that record and analyze flow data.<br><br>Key Aspects of a Meter Stream:<br>- Status: Indicates whether the meter stream is active or inactive.<br>- Measurement System Association: Links the meter stream to a specific measurement system, ensuring that the data collected corresponds to a defined physical setup.<br>- Flow Computer Association: Identifies the flow computer responsible for managing and recording the measurement system's data.<br>Why is a Meter Stream Important?<br>A **meter stream** is a critical component in flow measurement, as it ensures that the measurement system is correctly integrated into the flow computer for accurate monitoring and reporting. Since each flow computer can handle multiple meter streams, proper configuration is essential for maintaining data integrity and traceability.
|0.1
| - 損失函數:
CoSENTLoss
,參數如下:
{
"scale": 20.0,
"similarity_fct": "pairwise_cos_sim"
}
訓練超參數
非默認超參數
eval_strategy
:按步數評估per_device_train_batch_size
:4per_device_eval_batch_size
:4gradient_accumulation_steps
:4learning_rate
:2e-05num_train_epochs
:10warmup_ratio
:0.1
所有超參數
點擊展開
overwrite_output_dir
: Falsedo_predict
: Falseeval_strategy
: stepsprediction_loss_only
: Trueper_device_train_batch_size
: 4per_device_eval_batch_size
: 4per_gpu_train_batch_size
: Noneper_gpu_eval_batch_size
: Nonegradient_accumulation_steps
: 4eval_accumulation_steps
: Nonetorch_empty_cache_steps
: Nonelearning_rate
: 2e-05weight_decay
: 0.0adam_beta1
: 0.9adam_beta2
: 0.999adam_epsilon
: 1e-08max_grad_norm
: 1.0num_train_epochs
: 10max_steps
: -1lr_scheduler_type
: linearlr_scheduler_kwargs
: {}warmup_ratio
: 0.1warmup_steps
: 0log_level
: passivelog_level_replica
: warninglog_on_each_node
: Truelogging_nan_inf_filter
: Truesave_safetensors
: Truesave_on_each_node
: Falsesave_only_model
: Falserestore_callback_states_from_checkpoint
: Falseno_cuda
: Falseuse_cpu
: Falseuse_mps_device
: Falseseed
: 42data_seed
: Nonejit_mode_eval
: Falseuse_ipex
: Falsebf16
: Falsefp16
: Falsefp16_opt_level
: O1half_precision_backend
: autobf16_full_eval
: Falsefp16_full_eval
: Falsetf32
: Nonelocal_rank
: 0ddp_backend
: Nonetpu_num_cores
: Nonetpu_metrics_debug
: Falsedebug
: []dataloader_drop_last
: Falsedataloader_num_workers
: 0dataloader_prefetch_factor
: Nonepast_index
: -1disable_tqdm
: Falseremove_unused_columns
: Truelabel_names
: Noneload_best_model_at_end
: Falseignore_data_skip
: Falsefsdp
: []fsdp_min_num_params
: 0fsdp_config
: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}fsdp_transformer_layer_cls_to_wrap
: Noneaccelerator_config
: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}deepspeed
: Nonelabel_smoothing_factor
: 0.0optim
: adamw_torchoptim_args
: Noneadafactor
: Falsegroup_by_length
: Falselength_column_name
: lengthddp_find_unused_parameters
: Noneddp_bucket_cap_mb
: Noneddp_broadcast_buffers
: Falsedataloader_pin_memory
: Truedataloader_persistent_workers
: Falseskip_memory_metrics
: Trueuse_legacy_prediction_loop
: Falsepush_to_hub
: Falseresume_from_checkpoint
: Nonehub_model_id
: Nonehub_strategy
: every_savehub_private_repo
: Nonehub_always_push
: Falsegradient_checkpointing
: Falsegradient_checkpointing_kwargs
: Noneinclude_inputs_for_metrics
: Falseinclude_for_metrics
: []eval_do_concat_batches
: Truefp16_backend
: autopush_to_hub_model_id
: Nonepush_to_hub_organization
: Nonemp_parameters
:auto_find_batch_size
: Falsefull_determinism
: Falsetorchdynamo
: Noneray_scope
: lastddp_timeout
: 1800torch_compile
: Falsetorch_compile_backend
: Nonetorch_compile_mode
: Nonedispatch_batches
: Nonesplit_batches
: Noneinclude_tokens_per_second
: Falseinclude_num_input_tokens_seen
: Falseneftune_noise_alpha
: Noneoptim_target_modules
: Nonebatch_eval_metrics
: Falseeval_on_start
: Falseuse_liger_kernel
: Falseeval_use_gather_object
: Falseaverage_tokens_across_devices
: Falseprompts
: Nonebatch_sampler
: batch_samplermulti_dataset_batch_sampler
: proportional
訓練日誌
點擊展開
輪次 | 步數 | 訓練損失 | 驗證損失 |
---|---|---|---|
2.3953 | 460 | 0.8121 | - |
2.4473 | 470 | 1.7843 | - |
2.4993 | 480 | 3.0975 | - |
2.5514 | 490 | 0.8585 | - |
2.6034 | 500 | 2.7931 | - |
2.6554 | 510 | 1.4479 | - |
2.7074 | 520 | 1.6132 | - |
2.7594 | 530 | 0.8279 | - |
2.8114 | 540 | 2.0968 | - |
2.8635 | 550 | 1.5086 | - |
2.9155 | 560 | 1.7022 | - |
2.9675 | 570 | 1.7252 | - |
3.0208 | 580 | 0.329 | - |
3.0728 | 590 | 3.0231 | - |
3.1248 | 600 | 1.2077 | 0.4939 |
3.1769 | 610 | 1.7389 | - |
3.2289 | 620 | 1.747 | - |
3.2809 | 630 | 2.608 | - |
3.3329 | 640 | 2.3748 | - |
3.3849 | 650 | 0.9898 | - |
3.4369 | 660 | 3.6768 | - |
3.4889 | 670 | 1.7257 | - |
3.5410 | 680 | 1.2324 | - |
3.5930 | 690 | 1.4847 | - |
3.6450 | 700 | 0.5312 | - |
3.6970 | 710 | 2.6352 | - |
3.7490 | 720 | 3.3293 | - |
3.8010 | 730 | 1.0756 | - |
3.8531 | 740 | 1.2176 | - |
3.9051 | 750 | 1.4641 | 0.2318 |
3.9571 | 760 | 0.4642 | - |
4.0052 | 770 | 0.8467 | - |
4.0572 | 780 | 0.6422 | - |
4.1092 | 790 | 1.2341 | - |
4.1612 | 800 | 1.2382 | - |
4.2133 | 810 | 0.8518 | - |
4.2653 | 820 | 2.2545 | - |
4.3173 | 830 | 1.0461 | - |
4.3693 | 840 | 1.4097 | - |
4.4213 | 850 | 1.6382 | - |
4.4733 | 860 | 3.3653 | - |
4.5254 | 870 | 1.6778 | - |
4.5774 | 880 | 2.4592 | - |
4.6294 | 890 | 2.3244 | - |
4.6814 | 900 | 0.7048 | 0.2351 |
4.7334 | 910 | 1.507 | - |
4.7854 | 920 | 1.9508 | - |
4.8375 | 930 | 0.9046 | - |
4.8895 | 940 | 1.3923 | - |
4.9415 | 950 | 2.8222 | - |
4.9935 | 960 | 0.8341 | - |
5.0416 | 970 | 1.7129 | - |
5.0936 | 980 | 0.5792 | - |
5.1456 | 990 | 1.5091 | - |
5.1977 | 1000 | 0.8392 | - |
5.2497 | 1010 | 1.3499 | - |
5.3017 | 1020 | 1.1315 | - |
5.3537 | 1030 | 0.8192 | - |
5.4057 | 1040 | 0.3839 | - |
5.4577 | 1050 | 0.887 | 0.3572 |
5.5098 | 1060 | 0.9957 | - |
5.5618 | 1070 | 1.4341 | - |
5.6138 | 1080 | 0.5888 | - |
5.6658 | 1090 | 1.4963 | - |
5.7178 | 1100 | 1.5912 | - |
5.7698 | 1110 | 1.3382 | - |
5.8218 | 1120 | 1.4406 | - |
5.8739 | 1130 | 1.0845 | - |
5.9259 | 1140 | 0.2931 | - |
5.9779 | 1150 | 0.8994 | - |
6.0260 | 1160 | 1.1391 | - |
6.0780 | 1170 | 1.4646 | - |
6.1300 | 1180 | 0.509 | - |
6.1821 | 1190 | 0.4108 | - |
6.2341 | 1200 | 0.418 | 0.2573 |
6.2861 | 1210 | 1.4609 | - |
6.3381 | 1220 | 1.4237 | - |
6.3901 | 1230 | 0.6612 | - |
6.4421 | 1240 | 1.52 | - |
6.4941 | 1250 | 0.9426 | - |
6.5462 | 1260 | 1.5047 | - |
6.5982 | 1270 | 0.2918 | - |
6.6502 | 1280 | 0.96 | - |
6.7022 | 1290 | 1.6685 | - |
6.7542 | 1300 | 0.6779 | - |
6.8062 | 1310 | 0.0522 | - |
6.8583 | 1320 | 1.5055 | - |
6.9103 | 1330 | 0.2947 | - |
6.9623 | 1340 | 0.7499 | - |
7.0104 | 1350 | 2.6794 | 0.1881 |
7.0624 | 1360 | 1.4322 | - |
7.1144 | 1370 | 0.1859 | - |
7.1664 | 1380 | 1.0946 | - |
7.2185 | 1390 | 1.0941 | - |
7.2705 | 1400 | 0.8873 | - |
7.3225 | 1410 | 0.3996 | - |
7.3745 | 1420 | 0.159 | - |
7.4265 | 1430 | 0.7672 | - |
7.4785 | 1440 | 0.6511 | - |
7.5306 | 1450 | 0.2682 | - |
7.5826 | 1460 | 1.5488 | - |
7.6346 | 1470 | 0.4513 | - |
7.6866 | 1480 | 0.7482 | - |
7.7386 | 1490 | 1.4327 | - |
7.7906 | 1500 | 1.0277 | 0.1801 |
7.8427 | 1510 | 0.4197 | - |
7.8947 | 1520 | 3.3415 | - |
7.9467 | 1530 | 0.7131 | - |
7.9987 | 1540 | 0.7276 | - |
8.0468 | 1550 | 1.1939 | - |
8.0988 | 1560 | 0.4333 | - |
8.1508 | 1570 | 1.3594 | - |
8.2029 | 1580 | 0.9792 | - |
8.2549 | 1590 | 0.4581 | - |
8.3069 | 1600 | 0.5785 | - |
8.3589 | 1610 | 0.4015 | - |
8.4109 | 1620 | 0.5693 | - |
8.4629 | 1630 | 1.4925 | - |
8.5150 | 1640 | 0.6028 | - |
8.5670 | 1650 | 0.2087 | 0.1802 |
8.6190 | 1660 | 1.0404 | - |
8.6710 | 1670 | 0.8293 | - |
8.7230 | 1680 | 1.1231 | - |
8.7750 | 1690 | 0.4747 | - |
8.8270 | 1700 | 1.0668 | - |
8.8791 | 1710 | 1.2665 | - |
8.9311 | 1720 | 0.3004 | - |
8.9831 | 1730 | 0.1333 | - |
9.0312 | 1740 | 1.0171 | - |
9.0832 | 1750 | 1.3999 | - |
9.1352 | 1760 | 0.1939 | - |
9.1873 | 1770 | 0.1591 | - |
9.2393 | 1780 | 0.1243 | - |
9.2913 | 1790 | 0.8689 | - |
9.3433 | 1800 | 0.4325 | 0.1501 |
9.3953 | 1810 | 0.5094 | - |
9.4473 | 1820 | 0.3178 | - |
9.4993 | 1830 | 0.211 | - |
9.5514 | 1840 | 1.3497 | - |
9.6034 | 1850 | 0.6287 | - |
9.6554 | 1860 | 0.4895 | - |
9.7074 | 1870 | 0.3925 | - |
9.7594 | 1880 | 0.4384 | - |
9.8114 | 1890 | 0.8487 | - |
9.8635 | 1900 | 0.9134 | - |
9.9155 | 1910 | 0.1522 | - |
9.9675 | 1920 | 0.3798 | - |
框架版本
- Python: 3.11.0
- Sentence Transformers: 3.4.1
- Transformers: 4.49.0
- PyTorch: 2.6.0+cu124
- Accelerate: 1.4.0
- Datasets: 3.3.2
- Tokenizers: 0.21.0
📄 許可證
文檔中未提及相關信息。
📖 引用
BibTeX
Sentence Transformers
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/1908.10084",
}
CoSENTLoss
@online{kexuefm-8847,
title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
author={Su Jianlin},
year={2022},
month={Jan},
url={https://kexue.fm/archives/8847},
}
Jina Embeddings V3
Jina Embeddings V3 是一個多語言句子嵌入模型,支持超過100種語言,專注於句子相似度和特徵提取任務。
文本嵌入
Transformers 支持多種語言

J
jinaai
3.7M
911
Ms Marco MiniLM L6 V2
Apache-2.0
基於MS Marco段落排序任務訓練的交叉編碼器模型,用於信息檢索中的查詢-段落相關性評分
文本嵌入 英語
M
cross-encoder
2.5M
86
Opensearch Neural Sparse Encoding Doc V2 Distill
Apache-2.0
基於蒸餾技術的稀疏檢索模型,專為OpenSearch優化,支持免推理文檔編碼,在搜索相關性和效率上優於V1版本
文本嵌入
Transformers 英語

O
opensearch-project
1.8M
7
Sapbert From PubMedBERT Fulltext
Apache-2.0
基於PubMedBERT的生物醫學實體表徵模型,通過自對齊預訓練優化語義關係捕捉
文本嵌入 英語
S
cambridgeltl
1.7M
49
Gte Large
MIT
GTE-Large 是一個強大的句子轉換器模型,專注於句子相似度和文本嵌入任務,在多個基準測試中表現出色。
文本嵌入 英語
G
thenlper
1.5M
278
Gte Base En V1.5
Apache-2.0
GTE-base-en-v1.5 是一個英文句子轉換器模型,專注於句子相似度任務,在多個文本嵌入基準測試中表現優異。
文本嵌入
Transformers 支持多種語言

G
Alibaba-NLP
1.5M
63
Gte Multilingual Base
Apache-2.0
GTE Multilingual Base 是一個多語言的句子嵌入模型,支持超過50種語言,適用於句子相似度計算等任務。
文本嵌入
Transformers 支持多種語言

G
Alibaba-NLP
1.2M
246
Polybert
polyBERT是一個化學語言模型,旨在實現完全由機器驅動的超快聚合物信息學。它將PSMILES字符串映射為600維密集指紋,以數值形式表示聚合物化學結構。
文本嵌入
Transformers

P
kuelumbus
1.0M
5
Bert Base Turkish Cased Mean Nli Stsb Tr
Apache-2.0
基於土耳其語BERT的句子嵌入模型,專為語義相似度任務優化
文本嵌入
Transformers 其他

B
emrecan
1.0M
40
GIST Small Embedding V0
MIT
基於BAAI/bge-small-en-v1.5模型微調的文本嵌入模型,通過MEDI數據集與MTEB分類任務數據集訓練,優化了檢索任務的查詢編碼能力。
文本嵌入
Safetensors 英語
G
avsolatorio
945.68k
29
精選推薦AI模型
Llama 3 Typhoon V1.5x 8b Instruct
專為泰語設計的80億參數指令模型,性能媲美GPT-3.5-turbo,優化了應用場景、檢索增強生成、受限生成和推理任務
大型語言模型
Transformers 支持多種語言

L
scb10x
3,269
16
Cadet Tiny
Openrail
Cadet-Tiny是一個基於SODA數據集訓練的超小型對話模型,專為邊緣設備推理設計,體積僅為Cosmo-3B模型的2%左右。
對話系統
Transformers 英語

C
ToddGoldfarb
2,691
6
Roberta Base Chinese Extractive Qa
基於RoBERTa架構的中文抽取式問答模型,適用於從給定文本中提取答案的任務。
問答系統 中文
R
uer
2,694
98