Sentence Similarity
sentence-transformers
PyTorch
ONNX
Safetensors
OpenVINO
Transformers
English
mpnet
fill-mask
feature-extraction
text-embeddings-inference
Instructions to use Portgas37/MNLP_M2_document_encoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Portgas37/MNLP_M2_document_encoder with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Portgas37/MNLP_M2_document_encoder") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Transformers
How to use Portgas37/MNLP_M2_document_encoder with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("Portgas37/MNLP_M2_document_encoder") model = AutoModelForMaskedLM.from_pretrained("Portgas37/MNLP_M2_document_encoder") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_name_or_path": "microsoft/mpnet-base", | |
| "architectures": [ | |
| "MPNetForMaskedLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": 0, | |
| "eos_token_id": 2, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 514, | |
| "model_type": "mpnet", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 1, | |
| "relative_attention_num_buckets": 32, | |
| "transformers_version": "4.8.2", | |
| "vocab_size": 30527 | |
| } | |