这是一个 sentence-transformers 模型:它将句子和段落映射到一个768维度的稠密向量空间,可以用于聚类或语义搜索等任务。
当你已经安装了 sentence-transformers 后,使用这个模型就变得很容易:
pip install -U sentence-transformers
然后你可以像这样使用模型:
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-uncased') embeddings = model.encode(sentences) print(embeddings)
如果没有安装 sentence-transformers ,你可以这样使用模型:首先将你的输入传递给变换器模型,然后在上下文词嵌入之上应用正确的汇聚操作。
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-uncased') model = AutoModel.from_pretrained('nickprock/sentence-bert-base-italian-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)
对于该模型的自动评估,请参阅 Sentence Embeddings Benchmark: https://seb.sbert.net
该模型是使用以下参数进行训练的:
数据加载器:
torch.utils.data.dataloader.DataLoader,长度为360,具有以下参数:
{'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
损失函数:
sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss
fit() 方法的参数:
{ "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 }
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}) )