---
title: gte_Qwen2-7B-instruct
canonical_url: "https://www.modelscope.cn/models/iic/gte_Qwen2-7B-instruct"
md_url: "https://www.modelscope.cn/models/iic/gte_Qwen2-7B-instruct.md"
repository: iic/gte_Qwen2-7B-instruct
chinese_name: "GTE文本向量-Qwen2-7B"
last_updated: 2025-06-12
pipeline_tag: sentence-embedding
tasks:
  - sentence-embedding
model_type:
  - qwen2
architectures:
  - Qwen2ForCausalLM
parameters: 7.6B
tensor_type:
  - F32
library_name:
  - pytorch
  - safetensors
frameworks:
  - Pytorch
inference_backends:
  - "deploy_task emb/text"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 641760
stars: 67
---

# gte_Qwen2-7B-instruct

> gte_Qwen2-7B-instruct - iic 在 ModelScope 开源的模型。GTE文本向量模型-Qwen2-7B

iic/gte_Qwen2-7B-instruct 是 ModelScope 魔搭社区上的 7.6B 参数sentence-embedding模型，可用 deploy_task emb/text、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: iic/gte_Qwen2-7B-instruct
- **Tasks**: sentence-embedding
- **Parameters**: 7.6B
- **Inference backends**: deploy_task emb/text, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Downloads**: 641760
- **Stars**: 67
- **Last updated**: 2025-06-12

Source: https://www.modelscope.cn/models/iic/gte_Qwen2-7B-instruct

---

## gte-Qwen2-7B-instruct

**gte-Qwen2-7B-instruct** is the latest addition to the gte embedding family. This model has been engineered starting from the [Qwen2-7B](https://modelscope.cn/models/qwen/Qwen2-7B/files) 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.

## Model Information
- Model Size: 7B
- Embedding Dimension: 4096
- Max Input Tokens: 32k

## 模型下载

SDK下载
```bash
#安装ModelScope
pip install modelscope
pip install sentence_transformers
```
```python
#SDK模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('iic/gte_Qwen2-7B-instruct')
```
Git下载
```
#Git模型下载
git clone https://www.modelscope.cn/iic/gte_Qwen2-7B-instruct.git
```

## Requirements
```
transformers>=4.39.2,<=4.48.3
flash_attn>=2.5.6
huggingface-hub<=0.25
```
## Usage 

### Sentence Transformers

```python
from sentence_transformers import SentenceTransformer
from modelscope import snapshot_download
model_dir = snapshot_download("iic/gte_Qwen2-7B-instruct")

model = SentenceTransformer(model_dir, 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](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

```python
import torch
import torch.nn.functional as F

from torch import Tensor
from modelscope 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('iic/gte_Qwen2-7B-instruct', trust_remote_code=True)
model = AutoModel.from_pretrained('iic/gte_Qwen2-7B-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-Qwen2-7B-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**](https://modelscope.cn/models/iic/gte_Qwen1.5-7B-instruct) | 67.34 | 69.52 |
| **gte-Qwen2-7B-instruct** |  **70.04** | **71.98**  |

## Community support

### Fine-tuning

GTE models can be fine-tuned with a third party framework SWIFT.

```shell
pip install ms-swift -U
```

```shell
# check: https://swift.readthedocs.io/en/latest/BestPractices/Embedding.html
nproc_per_node=8
NPROC_PER_NODE=$nproc_per_node \
swift sft \
    --model iic/gte_Qwen2-7B-instruct \
    --train_type lora \
    --dataset 'sentence-transformers/stsb' \
    --torch_dtype bfloat16 \
    --num_train_epochs 10 \
    --per_device_train_batch_size 2 \
    --per_device_eval_batch_size 1 \
    --gradient_accumulation_steps $(expr 64 / $nproc_per_node) \
    --eval_steps 100 \
    --save_steps 100 \
    --eval_strategy steps \
    --use_chat_template false \
    --save_total_limit 5 \
    --logging_steps 5 \
    --output_dir output \
    --warmup_ratio 0.05 \
    --learning_rate 5e-6 \
    --deepspeed zero3 \
    --dataloader_num_workers 4 \
    --task_type embedding \
    --loss_type cosine_similarity \
    --dataloader_drop_last true
```

## 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}
}
```