Bi Encoder Mnrl Dbmdz Bert Base Turkish Cased Margin 3.0 Msmarco Tr 10k

🚀 oguuzhansahin/bi-encoder-mnrl-dbmdz-bert-base-turkish-cased-margin_3.0-msmarco-tr-10k

這是一個 sentence-transformers 模型，它可以將句子和段落映射到一個 768 維的密集向量空間，可用於聚類或語義搜索等任務。

🚀 快速開始

當你安裝了 sentence-transformers 後，使用這個模型會變得很容易：

pip install -U sentence-transformers

然後你可以像這樣使用該模型：

💻 使用示例

基礎用法

from sentence_transformers import SentenceTransformer, util

model = SentenceTransformer('oguuzhansahin/bi-encoder-mnrl-dbmdz-bert-base-turkish-cased-margin_3.0-msmarco-tr-10k')

query = "İstanbul'un nüfusu kaçtır?"

sentences = ["İstanbul'da yaşayan insan sayısı 15 milyonu geçmiştir",
             "Londra'nın nüfusu yaklaşık 9 milyondur.",
             "İstanbul'da hayat çok zor."]

query_embedding = model.encode(query, convert_to_tensor=True)
sentence_embeddings = model.encode(sentences, show_progress_bar=True)

#Compute dot score between query and all document embeddings
scores = util.dot_score(query_embedding, sentence_embeddings)[0].cpu().tolist()

#Combine docs & scores
doc_score_pairs = list(zip(sentences, scores))

#Sort by decreasing score
doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)

#Output passages & scores
for doc, score in doc_score_pairs:
    print(score, doc)

## Expected Output:
400.1816711425781 | İstanbul'da yaşayan insan sayısı 15 milyonu geçmiştir
309.97796630859375 | Londra'nın nüfusu yaklaşık 9 milyondur.
133.04507446289062 | İstanbul'da hayat çok zor.

📚 詳細文檔

評估結果

該模型在 10k 查詢翻譯的 MSMARCO 開發數據集上進行了評估。

訓練

該模型使用以下參數進行訓練：

數據加載器

torch.utils.data.dataloader.DataLoader，長度為 311，參數如下：

{'batch_size': 32, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}

損失函數

sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss，參數如下：

{'scale': 20.0, 'similarity_fct': 'cos_sim'}

fit() 方法的參數

{
    "epochs": 5,
    "evaluation_steps": 500,
    "evaluator": "sentence_transformers.evaluation.InformationRetrievalEvaluator.InformationRetrievalEvaluator",
    "max_grad_norm": 1,
    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
    "optimizer_params": {
        "lr": 2e-05
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": null,
    "warmup_steps": 1000,
    "weight_decay": 0.01
}

完整模型架構

SentenceTransformer(
  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)

引用與作者

文檔中未提供相關信息。