charlesdedampierre/bunka-embedding
This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
Usage in Bunkatopics
You can use this LLM in the BunkaTopics package as following:
pip install bunkatopics
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)
Usage (Sentence-Transformers)
Using this model becomes easy when you have sentence-transformers installed:
pip install -U sentence-transformers
Then you can use the model like this:
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)
Usage (HuggingFace Transformers)
Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
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)
Evaluation Results
For an automated evaluation of this model, see the Sentence Embeddings Benchmark: https://seb.sbert.net
Full Model Architecture
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})
)