Views
No views yet
transformers>=4.39.2
flash_attn>=2.5.61from sentence_transformers import SentenceTransformer
2
3model = SentenceTransformer("Alibaba-NLP/gte-Qwen2-1.5B-instruct", trust_remote_code=True)
4# In case you want to reduce the maximum length:
5model.max_seq_length = 8192
6
7queries = [
8 "how much protein should a female eat",
9 "summit define",
10]
11documents = [
12 "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.",
13 "Definition of summit for English Language Learners. : 1 the highest point of a mountain : the top of a mountain. : 2 the highest level. : 3 a meeting or series of meetings between the leaders of two or more governments.",
14]
15
16query_embeddings = model.encode(queries, prompt_name="query")
17document_embeddings = model.encode(documents)
18
19scores = (query_embeddings @ document_embeddings.T) * 100
20print(scores.tolist())model.encode(queries, prompt="Instruct: ...\nQuery: " to use a custom prompt of your choice.1import torch
2import torch.nn.functional as F
3
4from torch import Tensor
5from transformers import AutoTokenizer, AutoModel
6
7
8def last_token_pool(last_hidden_states: Tensor,
9 attention_mask: Tensor) -> Tensor:
10 left_padding = (attention_mask[:, -1].sum() == attention_mask.shape[0])
11 if left_padding:
12 return last_hidden_states[:, -1]
13 else:
14 sequence_lengths = attention_mask.sum(dim=1) - 1
15 batch_size = last_hidden_states.shape[0]
16 return last_hidden_states[torch.arange(batch_size, device=last_hidden_states.device), sequence_lengths]
17
18
19def get_detailed_instruct(task_description: str, query: str) -> str:
20 return f'Instruct: {task_description}\nQuery: {query}'
21
22
23# Each query must come with a one-sentence instruction that describes the task
24task = 'Given a web search query, retrieve relevant passages that answer the query'
25queries = [
26 get_detailed_instruct(task, 'how much protein should a female eat'),
27 get_detailed_instruct(task, 'summit define')
28]
29# No need to add instruction for retrieval documents
30documents = [
31 "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.",
32 "Definition of summit for English Language Learners. : 1 the highest point of a mountain : the top of a mountain. : 2 the highest level. : 3 a meeting or series of meetings between the leaders of two or more governments."
33]
34input_texts = queries + documents
35
36tokenizer = AutoTokenizer.from_pretrained('Alibaba-NLP/gte-Qwen2-1.5B-instruct', trust_remote_code=True)
37model = AutoModel.from_pretrained('Alibaba-NLP/gte-Qwen2-1.5B-instruct', trust_remote_code=True)
38
39max_length = 8192
40
41# Tokenize the input texts
42batch_dict = tokenizer(input_texts, max_length=max_length, padding=True, truncation=True, return_tensors='pt')
43outputs = model(**batch_dict)
44embeddings = last_token_pool(outputs.last_hidden_state, batch_dict['attention_mask'])
45
46# normalize embeddings
47embeddings = F.normalize(embeddings, p=2, dim=1)
48scores = (embeddings[:2] @ embeddings[2:].T) * 100
49print(scores.tolist())| Model Name | MTEB(56) | C-MTEB(35) | MTEB-fr(26) | MTEB-pl(26) |
|---|---|---|---|---|
| bge-base-en-1.5 | 64.23 | - | - | - |
| bge-large-en-1.5 | 63.55 | - | - | - |
| gte-large-en-v1.5 | 65.39 | - | - | - |
| gte-base-en-v1.5 | 64.11 | - | - | - |
| mxbai-embed-large-v1 | 64.68 | - | - | - |
| acge_text_embedding | - | 69.07 | - | - |
| stella-mrl-large-zh-v3.5-1792d | - | 68.55 | - | - |
| gte-large-zh | - | 66.72 | - | - |
| multilingual-e5-base | 59.45 | 56.21 | - | - |
| multilingual-e5-large | 61.50 | 58.81 | - | - |
| e5-mistral-7b-instruct | 66.63 | 60.81 | - | - |
| gte-Qwen1.5-7B-instruct | 67.34 | 69.52 | - | - |
| NV-Embed-v1 | 69.32 | - | - | - |
| gte-Qwen2-7B-instruct | 70.24 | 72.05 | 68.25 | 67.86 |
| gte-Qwen2-1.5B-instruct | 67.16 | 67.65 | 66.60 | 64.04 |
| Models | Language | Max Sequence Length | Dimension | Model Size (Memory Usage, fp32) |
|---|---|---|---|---|
| GTE-large-zh | Chinese | 512 | 1024 | 1.25GB |
| GTE-base-zh | Chinese | 512 | 512 | 0.41GB |
| GTE-small-zh | Chinese | 512 | 512 | 0.12GB |
| GTE-large | English | 512 | 1024 | 1.25GB |
| GTE-base | English | 512 | 512 | 0.21GB |
| GTE-small | English | 512 | 384 | 0.10GB |
| GTE-large-en-v1.5 | English | 8192 | 1024 | 1.74GB |
| GTE-base-en-v1.5 | English | 8192 | 768 | 0.51GB |
| GTE-Qwen1.5-7B-instruct | Multilingual | 32000 | 4096 | 26.45GB |
| GTE-Qwen2-7B-instruct | Multilingual | 32000 | 3584 | 26.45GB |
| GTE-Qwen2-1.5B-instruct | Multilingual | 32000 | 1536 | 6.62GB |
@article{li2023towards,
title={Towards general text embeddings with multi-stage contrastive learning},
author={Li, Zehan and Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Pengjun and Zhang, Meishan},
journal={arXiv preprint arXiv:2308.03281},
year={2023}
}