gte-Qwen1.5-7B-instruct
gte-Qwen1.5-7B-instruct is the latest addition to the gte embedding family. This model has been engineered starting from the Qwen1.5-7B LLM, drawing on the robust natural language processing capabilities of the Qwen1.5-7B model. Enhanced through our sophisticated embedding training techniques, the model incorporates several key advancements:
- Integration of bidirectional attention mechanisms, enriching its contextual understanding.
- Instruction tuning, applied solely on the query side for streamlined efficiency
- Comprehensive training across a vast, multilingual text corpus spanning diverse domains and scenarios. This training leverages both weakly supervised and supervised data, ensuring the model's applicability across numerous languages and a wide array of downstream tasks.
We also present gte-base-en-v1.5 and gte-large-en-v1.5, SOTA English embedding models that achieve state-of-the-art scores on the MTEB benchmark within the same model size category and support the context length of up to 8192.
Model Information
- Model Size: 7B
- Embedding Dimension: 4096
- Max Input Tokens: 32k
Requirements
transformers>=4.39.2
flash_attn>=2.5.6
Usage
Sentence Transformers
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("Alibaba-NLP/gte-Qwen1.5-7B-instruct", trust_remote_code=True)
# In case you want to reduce the maximum length:
model.max_seq_length = 8192
queries = [
"how much protein should a female eat",
"summit define",
]
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.",
"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.",
]
query_embeddings = model.encode(queries, prompt_name="query")
document_embeddings = model.encode(documents)
scores = (query_embeddings @ document_embeddings.T) * 100
print(scores.tolist())
# [[70.00668334960938, 8.184843063354492], [14.62419319152832, 77.71407318115234]]
Observe the config_sentence_transformers.json to see all pre-built prompt names. Otherwise, you can use model.encode(queries, prompt="Instruct: ...\nQuery: "
to use a custom prompt of your choice.
Transformers
import torch
import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel
def last_token_pool(last_hidden_states: Tensor,
attention_mask: Tensor) -> Tensor:
left_padding = (attention_mask[:, -1].sum() == attention_mask.shape[0])
if left_padding:
return last_hidden_states[:, -1]
else:
sequence_lengths = attention_mask.sum(dim=1) - 1
batch_size = last_hidden_states.shape[0]
return last_hidden_states[torch.arange(batch_size, device=last_hidden_states.device), sequence_lengths]
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, 'summit define')
]
# 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.",
"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."
]
input_texts = queries + documents
tokenizer = AutoTokenizer.from_pretrained('Alibaba-NLP/gte-Qwen1.5-7B-instruct', trust_remote_code=True)
model = AutoModel.from_pretrained('Alibaba-NLP/gte-Qwen1.5-7B-instruct', trust_remote_code=True)
max_length = 8192
# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=max_length, padding=True, truncation=True, return_tensors='pt')
outputs = model(**batch_dict)
embeddings = last_token_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())
# [[70.00666809082031, 8.184867858886719], [14.62420654296875, 77.71405792236328]]
Evaluation
MTEB & C-MTEB
You can use the scripts/eval_mteb.py to reproduce the following result of gte-Qwen1.5-7B-instruct on MTEB(English)/C-MTEB(Chinese):
Model Name | MTEB(56) | C-MTEB(35) |
---|---|---|
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 |
Citation
If you find our paper or models helpful, please consider cite:
@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}
}
- Downloads last month
- 902
Spaces using Alibaba-NLP/gte-Qwen1.5-7B-instruct 5
Collection including Alibaba-NLP/gte-Qwen1.5-7B-instruct
Evaluation results
- accuracy on MTEB AmazonCounterfactualClassification (en)test set self-reported83.164
- ap on MTEB AmazonCounterfactualClassification (en)test set self-reported49.377
- f1 on MTEB AmazonCounterfactualClassification (en)test set self-reported77.530
- accuracy on MTEB AmazonPolarityClassificationtest set self-reported96.696
- ap on MTEB AmazonPolarityClassificationtest set self-reported94.909
- f1 on MTEB AmazonPolarityClassificationtest set self-reported96.695
- accuracy on MTEB AmazonReviewsClassification (en)test set self-reported62.168
- f1 on MTEB AmazonReviewsClassification (en)test set self-reported60.411
- map_at_1 on MTEB ArguAnatest set self-reported36.415
- map_at_10 on MTEB ArguAnatest set self-reported53.505