pkshatech/RoSEtta-base-ja

from sentence_transformers import SentenceTransformer
import torch.nn.functional as F

# Download from the 🤗 Hub
# The argument "trust_remote_code=True" is required to load the model
model = SentenceTransformer("pkshatech/RoSEtta-base-ja",trust_remote_code=True)

# Each input text should start with "query: " or "passage: ".
# For tasks other than retrieval, you can simply use the "query: " prefix.
sentences = [
    'query: PKSHAはどんな会社ですか？',
    'passage: 研究開発したアルゴリズムを、多くの企業のソフトウエア・オペレーションに導入しています。',
    'query: 日本で一番高い山は？',
    'passage: 富士山（ふじさん）は、標高3776.12 m、日本最高峰（剣ヶ峰）の独立峰で、その優美な風貌は日本国外でも日本の象徴として広く知られている。',
]
embeddings = model.encode(sentences,convert_to_tensor=True)
print(embeddings.shape)
# [4, 768]

# Get the similarity scores for the embeddings
similarities = F.cosine_similarity(embeddings.unsqueeze(0), embeddings.unsqueeze(1), dim=2)
print(similarities)
# [[1.0000, 0.5910, 0.4332, 0.5421],
# [0.5910, 1.0000, 0.4977, 0.6969],
# [0.4332, 0.4977, 1.0000, 0.7475],
# [0.5421, 0.6969, 0.7475, 1.0000]]

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

def mean_pooling(last_hidden_states: Tensor,attention_mask: Tensor) -> Tensor:
    emb = last_hidden_states * attention_mask.unsqueeze(-1)
    emb = emb.sum(dim=1) / attention_mask.sum(dim=1).unsqueeze(-1)
    return emb

# Download from the 🤗 Hub
tokenizer = AutoTokenizer.from_pretrained("pkshatech/RoSEtta-base-ja")
# The argument "trust_remote_code=True" is required to load the model
model = AutoModel.from_pretrained("pkshatech/RoSEtta-base-ja",trust_remote_code=True)

# Each input text should start with "query: " or "passage: ".
# For tasks other than retrieval, you can simply use the "query: " prefix.
sentences = [
    'query: PKSHAはどんな会社ですか？',
    'passage: 研究開発したアルゴリズムを、多くの企業のソフトウエア・オペレーションに導入しています。',
    'query: 日本で一番高い山は？',
    'passage: 富士山（ふじさん）は、標高3776.12 m、日本最高峰（剣ヶ峰）の独立峰で、その優美な風貌は日本国外でも日本の象徴として広く知られている。',
]

# Tokenize the input texts
batch_dict = tokenizer(sentences, max_length=1024, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = mean_pooling(outputs.last_hidden_state, batch_dict['attention_mask'])
print(embeddings.shape)
# [4, 768]

# Get the similarity scores for the embeddings
similarities = F.cosine_similarity(embeddings.unsqueeze(0), embeddings.unsqueeze(1), dim=2)
print(similarities)
# [[1.0000, 0.5910, 0.4332, 0.5421],
# [0.5910, 1.0000, 0.4977, 0.6969],
# [0.4332, 0.4977, 1.0000, 0.7475],
# [0.5421, 0.6969, 0.7475, 1.0000]]