Bunka Embedding

🚀 charlesdedampierre/bunka-embedding

這是一個 sentence-transformers 模型，它可以將句子和段落映射到一個 768 維的密集向量空間，可用於聚類或語義搜索等任務。

🚀 快速開始

本模型可用於句子相似度計算，能將文本轉換為向量，在聚類、語義搜索等場景發揮作用。

✨ 主要特性

• 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。

📦 安裝指南

在 Bunkatopics 中使用

你可以按照以下步驟在 BunkaTopics 包中使用此大語言模型：

pip install bunkatopics

使用 Sentence-Transformers

如果你已經安裝了 sentence-transformers，使用此模型會很簡單：

pip install -U sentence-transformers

💻 使用示例

在 Bunkatopics 中使用

from bunkatopics import Bunka
import random
from datasets import load_dataset

dataset = load_dataset("rguo123/trump_tweets")['train']['content']
full_docs = random.sample(dataset, 10000)

from langchain.embeddings import HuggingFaceEmbeddings

embedding_model = HuggingFaceEmbeddings(model_name="charlesdedampierre/bunka-embedding")

bunka = Bunka(model_hf=embedding_model)

bunka.fit(full_docs)
df_topics = bunka.get_topics(n_clusters = 20)

使用 Sentence-Transformers

from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]

model = SentenceTransformer('charlesdedampierre/bunka-embedding')
embeddings = model.encode(sentences)
print(embeddings)

使用 HuggingFace Transformers

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 = ['This is an example sentence', 'Each sentence is converted']

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('charlesdedampierre/bunka-llms')
model = AutoModel.from_pretrained('charlesdedampierre/bunka-llms')

# 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

有關此模型的自動評估，請參閱 Sentence Embeddings Benchmark：https://seb.sbert.net

完整模型架構

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: RobertaModel 
  (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

本項目採用 MIT 許可證。