Views
No views yet
1from sentence_transformers import SentenceTransformer
2sentences = ["At 8pm protesters gathered on the main square and shouted 'end fossil fuels'", "The German government demonstrated composure in its reaction to social media posts"]
3
4model = SentenceTransformer('{MODEL_NAME}')
5embeddings = model.encode(sentences)
6
7# Sentences we want sentence embeddings for
8sentences = ["At 8pm protesters gathered on the main square and shouted 'end fossil fuels'", "The German government demonstrated composure in its reaction to social media posts"]
9
10# Load model from HuggingFace Hub
11tokenizer = AutoTokenizer.from_pretrained('shaunss/protestforms_mpnet-base-v2')
12model = AutoModel.from_pretrained('shaunss/protestforms_mpnet-base-v2')
13
14# Tokenize sentences
15encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')torch.utils.data.dataloader.DataLoader of length 681 with parameters:{'batch_size': 32, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}sentence_transformers.losses.BatchSemiHardTripletLoss.BatchSemiHardTripletLoss{
"epochs": 10,
"evaluation_steps": 2177.5,
"evaluator": "sentence_transformers.evaluation.BinaryClassificationEvaluator.BinaryClassificationEvaluator",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 2177.5,
"weight_decay": 0.01
}SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
(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})
)