how to extract embedding for retrieval task

#10
by Ratar37003 - opened

how can i use this model for retreival task , idont see any example for this other mask modelling

can i use this way

'import torch.nn.functional as F

from torch import Tensor
from transformers import AutoTokenizer, AutoModel

def average_pool(last_hidden_states: Tensor,
attention_mask: Tensor) -> Tensor:
last_hidden = last_hidden_states.masked_fill(~attention_mask[..., None].bool(), 0.0)
return last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None]

def get_detailed_instruct(task_description: str, query: str) -> str:
return f'Instruct: {task_description}\nQuery: {query}'

Each query must come with a one-sentence instruction that describes the task

task = 'Given a web search query, retrieve relevant passages that answer the query'
queries = [
get_detailed_instruct(task, 'how much protein should a female eat'),
get_detailed_instruct(task, 'ๅ—็“œ็š„ๅฎถๅธธๅšๆณ•')
]

No need to add instruction for retrieval documents

documents = [
"As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.",
"1.ๆธ…็‚’ๅ—็“œไธ ๅŽŸๆ–™:ๅซฉๅ—็“œๅŠไธช ่ฐƒๆ–™:่‘ฑใ€็›ใ€็™ฝ็ณ–ใ€้ธก็ฒพ ๅšๆณ•: 1ใ€ๅ—็“œ็”จๅˆ€่–„่–„็š„ๅ‰ŠๅŽป่กจ้ขไธ€ๅฑ‚็šฎ,็”จๅ‹บๅญๅˆฎๅŽป็“ค 2ใ€ๆ“ฆๆˆ็ป†ไธ(ๆฒกๆœ‰ๆ“ฆ่œๆฟๅฐฑ็”จๅˆ€ๆ…ขๆ…ขๅˆ‡ๆˆ็ป†ไธ) 3ใ€้”…็ƒง็ƒญๆ”พๆฒน,ๅ…ฅ่‘ฑ่Šฑ็…ธๅ‡บ้ฆ™ๅ‘ณ 4ใ€ๅ…ฅๅ—็“œไธๅฟซ้€Ÿ็ฟป็‚’ไธ€ๅˆ†้’Ÿๅทฆๅณ,ๆ”พ็›ใ€ไธ€็‚น็™ฝ็ณ–ๅ’Œ้ธก็ฒพ่ฐƒๅ‘ณๅ‡บ้”… 2.้ฆ™่‘ฑ็‚’ๅ—็“œ ๅŽŸๆ–™:ๅ—็“œ1ๅช ่ฐƒๆ–™:้ฆ™่‘ฑใ€่’œๆœซใ€ๆฉ„ๆฆ„ๆฒนใ€็› ๅšๆณ•: 1ใ€ๅฐ†ๅ—็“œๅŽป็šฎ,ๅˆ‡ๆˆ็‰‡ 2ใ€ๆฒน้”…8ๆˆ็ƒญๅŽ,ๅฐ†่’œๆœซๆ”พๅ…ฅ็ˆ†้ฆ™ 3ใ€็ˆ†้ฆ™ๅŽ,ๅฐ†ๅ—็“œ็‰‡ๆ”พๅ…ฅ,็ฟป็‚’ 4ใ€ๅœจ็ฟป็‚’็š„ๅŒๆ—ถ,ๅฏไปฅไธๆ—ถๅœฐๅพ€้”…้‡ŒๅŠ ๆฐด,ไฝ†ไธ่ฆๅคชๅคš 5ใ€ๆ”พๅ…ฅ็›,็‚’ๅŒ€ 6ใ€ๅ—็“œๅทฎไธๅคš่ฝฏๅ’Œ็ปตไบ†ไน‹ๅŽ,ๅฐฑๅฏไปฅๅ…ณ็ซ 7ใ€ๆ’’ๅ…ฅ้ฆ™่‘ฑ,ๅณๅฏๅ‡บ้”…"
]
input_texts = queries + documents

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModel.from_pretrained(model_id)

Tokenize the input texts

batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = average_pool(outputs.last_hidden_state, batch_dict['attention_mask'])

normalize embeddings

embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:2] @ embeddings[2:].T) * 100
print(scores.tolist())

=> [[91.92852783203125, 67.580322265625], [70.3814468383789, 92.1330795288086]]

'

EuroBERT org

Hello!

This model is currently only good at "mask filling", i.e. if you have a sentence like "I love going to [MASK]", it can predict the mask.
To turn this into an embedding model that's good for retrieval, someone has to finetune it on a question-answer or information retrieval dataset, e.g. with Sentence Transformers: https://sbert.net/
Currently, this has only been done for Arabic models: https://huggingface.co/models?library=sentence-transformers&other=eurobert&sort=trending

  • Tom Aarsen

Sign up or log in to comment