Sentence Bert Base Italian Xxl Uncased

🚀 意大利語基礎句向量模型 sentence-bert-base-italian-xxl-cased

該模型基於 sentence-transformers 構建，可將句子和段落映射到 768 維的密集向量空間，適用於聚類、語義搜索等任務。它源自 dbmdz/bert-base-italian-xxl-uncased，更多信息可查看其模型卡片。

🚀 快速開始

本模型支持多種使用方式，以下將分別介紹不同庫下的使用方法。

📦 安裝指南

使用 sentence-transformers 庫

若要使用 sentence-transformers 庫，可通過以下命令進行安裝：

pip install -U sentence-transformers

使用 FastEmbed 庫

若要使用 FastEmbed 庫，可通過以下命令進行安裝：

pip install fastembed

💻 使用示例

使用 sentence-transformers 庫

from sentence_transformers import SentenceTransformer
sentences = ["Una ragazza si acconcia i capelli.", "Una ragazza si sta spazzolando i capelli."]

model = SentenceTransformer('nickprock/sentence-bert-base-italian-xxl-uncased')
embeddings = model.encode(sentences)
print(embeddings)

使用 FastEmbed 庫

from fastembed import TextEmbedding
from fastembed.common.model_description import PoolingType, ModelSource

sentences = ["Una ragazza si acconcia i capelli.", "Una ragazza si sta spazzolando i capelli."]

TextEmbedding.add_custom_model(
    model="nickprock/sentence-bert-base-italian-xxl-uncased",
    pooling=PoolingType.MEAN,
    normalization=True,
    sources=ModelSource(hf="nickprock/sentence-bert-base-italian-xxl-uncased"),  # can be used with an `url` to load files from a private storage
    dim=768,
    model_file="onnx/model_qint8_avx512_vnni.onnx",  # can be used to load an already supported model with another optimization or quantization, e.g. onnx/model_O4.onnx
)

model = TextEmbedding(model_name="nickprock/sentence-bert-base-italian-xxl-uncased")
embeddings = list(model.embed(sentences))
print(embeddings)

使用 HuggingFace Transformers 庫

若不使用 sentence-transformers 庫，可按以下方式使用模型：首先將輸入傳遞給 Transformer 模型，然後對上下文詞嵌入應用正確的池化操作。

from transformers import AutoTokenizer, AutoModel
import torch


#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)


# Sentences we want sentence embeddings for
sentences = ['Una ragazza si acconcia i capelli.', 'Una ragazza si sta spazzolando i capelli.']

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('nickprock/sentence-bert-base-italian-xxl-uncased')
model = AutoModel.from_pretrained('nickprock/sentence-bert-base-italian-xxl-uncased')

# 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, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

print("Sentence embeddings:")
print(sentence_embeddings)

📚 詳細文檔

評估結果

若要對本模型進行自動化評估，可參考 Sentence Embeddings Benchmark：https://seb.sbert.net

訓練參數

本模型的訓練參數如下：

DataLoader

使用 torch.utils.data.dataloader.DataLoader，長度為 360，參數如下：

{'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}

損失函數

使用 sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss 損失函數。

fit() 方法參數

{
    "epochs": 10,
    "evaluation_steps": 500,
    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
    "max_grad_norm": 1,
    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
    "optimizer_params": {
        "lr": 2e-05
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": 1500,
    "warmup_steps": 360,
    "weight_decay": 0.01
}

完整模型架構

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, '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})
)

📄 許可證

本模型採用 MIT 許可證。