---
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- dense
- generated_from_trainer
- dataset_size:69363
- loss:EpochLossWrapper
base_model: intfloat/multilingual-e5-large
widget:
- source_sentence: 'query: MSI 微星 MSI PRO MP165 E6 可攜式螢幕 (16型/FHD/Type C/喇叭/IPS)+SPACE
LED觸控護眼三色螢幕掛燈 33cm款'
sentences:
- 'passage: 六合一清潔組【Apple】AirPods 4'
- 'passage: 【MSI 微星】PRO MP251 E2 25型 平面商用螢幕(FHD/IPS/120Hz/DP+HDMI+D-Sub/眼部護理技術)'
- 'passage: 【Apple】Apple Watch Series 11 GPS+行動網路 42mm(鋁金屬錶殼搭配運動型錶帶)'
- source_sentence: 'query: DAIKIN 大金 7坪閃流放電空氣清淨機 MC30YSCT'
sentences:
- 'passage: 三合一充電座組【Apple】Apple Watch Ultra 3 GPS+行動網路 49mm(鈦金屬錶殼搭配越野錶環)'
- 'passage: 【LG 樂金】58H快配17公斤◆AI DD™智慧直驅變頻洗衣機 ◆曜石黑(WT-VDN17M)'
- 'passage: 【LG 樂金】PuriCare Hit 一級能效 超淨化 大白 抗敏 空氣 清淨機 適用18坪 / 台 AS601HWG0'
- source_sentence: 'query: Logitech 羅技 G304 LIGHTSPEED 無線電競遊戲滑鼠 黑色'
sentences:
- 'passage: 【grantclassic】6入濾心套餐組 喝不停 AquaLux 寵物智能陶瓷飲水機 + 6入專用濾心(2L/官方品牌館)'
- 'passage: 【Logitech 羅技】M190無線滑鼠(黑色)'
- 'passage: 【beyerdynamic】DT 71 IE 鼓組&貝斯 入耳式監聽耳機 #劇院視聽 #HIFI #高解析音質 #有線耳機(公司貨保證)'
- source_sentence: 'query: KINTO / TRAVEL TUMBLER 隨行保溫瓶500ml-灰'
sentences:
- 'passage: 【小不記】1080P旗艦款-多媒體投影儀 4K畫質智慧投影機 LED鏡像同屏(家用投影機 露營投影機 投影機)'
- 'passage: 手提陶瓷咖啡保溫杯500ml(內附吸管/五色任選/保冰杯/保溫杯/減塑/保溫瓶)'
- 'passage: 【技嘉】顯卡+電源組合★ RTX 5080 GAMING OC 16G 顯示卡+海韻 ATX3 Core GX-850 金牌電源供應器'
- source_sentence: 'query: PHILIPS 飛利浦 Sonicare 智慧感應型電動牙刷 新月白 (HX6877/27)'
sentences:
- 'passage: 【MSI 微星】MSI 微星 MAG 274UPDF E16M 電競螢幕 27吋 160Hz 4k IPS 0.5ms HDR 可旋轉'
- 'passage: 【SHARP 夏普】12公升 自動除菌離子除濕機(DW-LT12ST-W)'
- 'passage: 【Philips 飛利浦】官方直Sonicare抗敏Pro 鑽石智能音波電動牙刷/護敏刷HX3892/02(雙入組)'
pipeline_tag: sentence-similarity
library_name: sentence-transformers
---
# SentenceTransformer based on intfloat/multilingual-e5-large
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large). It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
## Model Details
### Model Description
- **Model Type:** Sentence Transformer
- **Base model:** [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large)
- **Maximum Sequence Length:** 128 tokens
- **Output Dimensionality:** 1024 dimensions
- **Similarity Function:** Cosine Similarity
### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
### Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False, 'architecture': '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()
)
```
## Usage
### Direct Usage (Sentence Transformers)
First install the Sentence Transformers library:
```bash
pip install -U sentence-transformers
```
Then you can load this model and run inference.
```python
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
'query: PHILIPS 飛利浦 Sonicare 智慧感應型電動牙刷 新月白 (HX6877/27)',
'passage: 【Philips 飛利浦】官方直Sonicare抗敏Pro 鑽石智能音波電動牙刷/護敏刷HX3892/02(雙入組)',
'passage: 【SHARP 夏普】12公升 自動除菌離子除濕機(DW-LT12ST-W)',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.1586, 0.0201],
# [0.1586, 1.0000, 0.1386],
# [0.0201, 0.1386, 1.0000]])
```
## Training Details
### Training Dataset
#### Unnamed Dataset
* Size: 69,363 training samples
* Columns: sentence_0, sentence_1, and label
* Approximate statistics based on the first 1000 samples:
| | sentence_0 | sentence_1 | label |
|:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------------------------|
| type | string | string | int |
| details |
query: Logitech 羅技 M221 靜音無線滑鼠-黑 | passage: 【Logitech 羅技】Pebble M350s 無線藍牙滑鼠 - 珍珠白(不附接收器) | 0 |
| query: Kleenex 舒潔 萬用輕巧包抽取衛生紙(110+20抽x20包/串) | passage: 【Kleenex 舒潔】棉柔舒適抽取衛生紙110抽*60包 | 0 |
| query: Apple 蘋果 Apple Watch Series 11 GPS + LTE 46mm 玫瑰金色鋁金屬錶殼搭配淡胭粉色運動錶帶 | passage: 【Apple】Apple Watch S11 GPS + 行動網路 46mm(鋁金屬錶殼搭配運動型錶帶) | 0 |
* Loss: __main__.EpochLossWrapper
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: steps
- `per_device_train_batch_size`: 32
- `per_device_eval_batch_size`: 32
- `num_train_epochs`: 15
- `fp16`: True
- `multi_dataset_batch_sampler`: round_robin
#### All Hyperparameters