--- title: gte-multilingual-base canonical_url: "https://www.modelscope.cn/models/iic/gte-multilingual-base" md_url: "https://www.modelscope.cn/models/iic/gte-multilingual-base.md" repository: iic/gte-multilingual-base last_updated: 2025-09-28 license: apache-2.0 pipeline_tag: sentence-similarity tasks: - sentence-similarity model_type: - new architectures: - NewModel - NewForTokenClassification parameters: 305.4M tensor_type: - F16 library_name: - pytorch - transformer - sentence-transformers - safetensors frameworks: - pytorch language: - af - ar - az - be - bg - bn - ca - ceb - cs - cy - da - de - el - en - es - et - eu - fa - fi - fr - gl - gu - he - hi - hr - ht - hu - hy - id - is - it - ja - jv - ka - kk - km - kn - ko - ky - lo - lt - lv - mk - ml - mn - mr - ms - my - ne - nl - no - pa - pl - pt - qu - ro - ru - si - sk - sl - so - sq - sr - sv - sw - ta - te - th - tl - tr - uk - ur - vi - yo - zh downloads: 375 stars: 1 tags: - mteb - sentence-transformers - transformers - multilingual - sentence-similarity - text-embeddings-inference --- # gte-multilingual-base > gte-multilingual-base - iic 在 ModelScope 开源的模型。gte-multilingual-base iic/gte-multilingual-base 是 ModelScope 魔搭社区上的 305.4M 参数sentence-similarity模型，采用 apache-2.0 许可。 - **Repository**: iic/gte-multilingual-base - **License**: apache-2.0 - **Tasks**: sentence-similarity - **Parameters**: 305.4M - **Tags**: mteb, sentence-transformers, transformers, multilingual, sentence-similarity, text-embeddings-inference - **Downloads**: 375 - **Stars**: 1 - **Last updated**: 2025-09-28 Source: https://www.modelscope.cn/models/iic/gte-multilingual-base --- ## gte-multilingual-base The **gte-multilingual-base** model is the latest in the [GTE](https://huggingface.co/collections/Alibaba-NLP/gte-models-6680f0b13f885cb431e6d469) (General Text Embedding) family of models, featuring several key attributes: - **High Performance**: Achieves state-of-the-art (SOTA) results in multilingual retrieval tasks and multi-task representation model evaluations when compared to models of similar size. - **Training Architecture**: Trained using an encoder-only transformers architecture, resulting in a smaller model size. Unlike previous models based on decode-only LLM architecture (e.g., gte-qwen2-1.5b-instruct), this model has lower hardware requirements for inference, offering a 10x increase in inference speed. - **Long Context**: Supports text lengths up to **8192** tokens. - **Multilingual Capability**: Supports over **70** languages. - **Elastic Dense Embedding**: Support elastic output dense representation while maintaining the effectiveness of downstream tasks, which significantly reduces storage costs and improves execution efficiency. - **Sparse Vectors**: In addition to dense representations, it can also generate sparse vectors. **Paper**: [mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval](https://arxiv.org/pdf/2407.19669) ## Model Information - Model Size: 305M - Embedding Dimension: 768 - Max Input Tokens: 8192 ## Usage - **It is recommended to install xformers and enable unpadding for acceleration, refer to [enable-unpadding-and-xformers](https://huggingface.co/Alibaba-NLP/new-impl#recommendation-enable-unpadding-and-acceleration-with-xformers).** - **How to use it offline: [new-impl/discussions/2](https://huggingface.co/Alibaba-NLP/new-impl/discussions/2#662b08d04d8c3d0a09c88fa3)** - **How to use with [TEI](https://github.com/huggingface/text-embeddings-inference): [refs/pr/7](https://huggingface.co/Alibaba-NLP/gte-multilingual-base/discussions/7#66bfb82ea03b764ca92a2221)** ### Get Dense Embeddings with Transformers ```python # Requires transformers>=4.36.0 import torch.nn.functional as F from transformers import AutoModel, AutoTokenizer input_texts = [ "what is the capital of China?", "how to implement quick sort in python?", "北京", "快排算法介绍" ] model_name_or_path = 'Alibaba-NLP/gte-multilingual-base' tokenizer = AutoTokenizer.from_pretrained(model_name_or_path) model = AutoModel.from_pretrained(model_name_or_path, trust_remote_code=True) # Tokenize the input texts batch_dict = tokenizer(input_texts, max_length=8192, padding=True, truncation=True, return_tensors='pt') outputs = model(**batch_dict) dimension=768 # The output dimension of the output embedding, should be in [128, 768] embeddings = outputs.last_hidden_state[:, 0][:dimension] embeddings = F.normalize(embeddings, p=2, dim=1) scores = (embeddings[:1] @ embeddings[1:].T) * 100 print(scores.tolist()) # [[0.3016996383666992, 0.7503870129585266, 0.3203084468841553]] ``` ### Use with sentence-transformers ```python # Requires sentence-transformers>=3.0.0 from sentence_transformers import SentenceTransformer input_texts = [ "what is the capital of China?", "how to implement quick sort in python?", "北京", "快排算法介绍" ] model_name_or_path="Alibaba-NLP/gte-multilingual-base" model = SentenceTransformer(model_name_or_path, trust_remote_code=True) embeddings = model.encode(input_texts, normalize_embeddings=True) # embeddings.shape (4, 768) # sim scores scores = model.similarity(embeddings[:1], embeddings[1:]) print(scores.tolist()) # [[0.301699697971344, 0.7503870129585266, 0.32030850648880005]] ``` ### Use with infinity Usage via docker and [infinity](https://github.com/michaelfeil/infinity), MIT Licensed. ``` docker run --gpus all -v $PWD/data:/app/.cache -p "7997":"7997" \ michaelf34/infinity:0.0.69 \ v2 --model-id Alibaba-NLP/gte-multilingual-base --revision "main" --dtype float16 --batch-size 32 --device cuda --engine torch --port 7997 ``` ### Use with Text Embeddings Inference (TEI) Usage via Docker and [Text Embeddings Inference (TEI)](https://github.com/huggingface/text-embeddings-inference): - CPU: ```bash docker run --platform linux/amd64 \ -p 8080:80 \ -v $PWD/data:/data \ --pull always \ ghcr.io/huggingface/text-embeddings-inference:cpu-1.7 \ --model-id Alibaba-NLP/gte-multilingual-base \ --dtype float16 ``` - GPU: ``` docker run --gpus all \ -p 8080:80 \ -v $PWD/data:/data \ --pull always \ ghcr.io/huggingface/text-embeddings-inference:1.7 \ --model-id Alibaba-NLP/gte-multilingual-base \ --dtype float16 ``` Then you can send requests to the deployed API via the OpenAI-compatible `v1/embeddings` route (more information about the [OpenAI Embeddings API](https://platform.openai.com/docs/api-reference/embeddings)): ```bash curl https://0.0.0.0:8080/v1/embeddings \ -H "Content-Type: application/json" \ -d '{ "input": [ "what is the capital of China?", "how to implement quick sort in python?", "北京", "快排算法介绍" ], "model": "Alibaba-NLP/gte-multilingual-base", "encoding_format": "float" }' ``` ### Use with custom code to get dense embeddings and sparse token weights ```python # You can find the script gte_embedding.py in https://huggingface.co/Alibaba-NLP/gte-multilingual-base/blob/main/scripts/gte_embedding.py from gte_embedding import GTEEmbeddidng model_name_or_path = 'Alibaba-NLP/gte-multilingual-base' model = GTEEmbeddidng(model_name_or_path) query = "中国的首都在哪儿" docs = [ "what is the capital of China?", "how to implement quick sort in python?", "北京", "快排算法介绍" ] embs = model.encode(docs, return_dense=True,return_sparse=True) print('dense_embeddings vecs', embs['dense_embeddings']) print('token_weights', embs['token_weights']) pairs = [(query, doc) for doc in docs] dense_scores = model.compute_scores(pairs, dense_weight=1.0, sparse_weight=0.0) sparse_scores = model.compute_scores(pairs, dense_weight=0.0, sparse_weight=1.0) hybrid_scores = model.compute_scores(pairs, dense_weight=1.0, sparse_weight=0.3) print('dense_scores', dense_scores) print('sparse_scores', sparse_scores) print('hybrid_scores', hybrid_scores) # dense_scores [0.85302734375, 0.257568359375, 0.76953125, 0.325439453125] # sparse_scores [0.0, 0.0, 4.600879669189453, 1.570279598236084] # hybrid_scores [0.85302734375, 0.257568359375, 2.1497951507568356, 0.7965233325958252] ``` ## Evaluation We validated the performance of the **gte-multilingual-base** model on multiple downstream tasks, including multilingual retrieval, cross-lingual retrieval, long text retrieval, and general text representation evaluation on the [MTEB Leaderboard](https://huggingface.co/spaces/mteb/leaderboard), among others. ### Retrieval Task Retrieval results on [MIRACL](https://arxiv.org/abs/2210.09984) and [MLDR](https://arxiv.org/abs/2402.03216) (multilingual), [MKQA](https://arxiv.org/abs/2007.15207) (crosslingual), [BEIR](https://arxiv.org/abs/2104.08663) and [LoCo](https://arxiv.org/abs/2402.07440) (English). ![image](./images/mgte-retrieval.png) - Detail results on [MLDR](https://arxiv.org/abs/2402.03216) ![image](./images/mgte-retrieval.png) - Detail results on [LoCo](https://arxiv.org/abs/2402.07440) ### MTEB Results on MTEB English, Chinese, French, Polish ![image](./images/mgte-mteb.png) **More detailed experimental results can be found in the [paper](https://arxiv.org/pdf/2407.19669)**. ## Cloud API Services In addition to the open-source [GTE](https://huggingface.co/collections/Alibaba-NLP/gte-models-6680f0b13f885cb431e6d469) series models, GTE series models are also available as commercial API services on Alibaba Cloud. - [Embedding Models](https://help.aliyun.com/zh/model-studio/developer-reference/general-text-embedding/): Three versions of the text embedding models are available: text-embedding-v1/v2/v3, with v3 being the latest API service. - [ReRank Models](https://help.aliyun.com/zh/model-studio/developer-reference/general-text-sorting-model/): The gte-rerank model service is available. Note that the models behind the commercial APIs are not entirely identical to the open-source models. ## Citation If you find our paper or models helpful, please consider cite: ``` @inproceedings{zhang2024mgte, title={mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval}, author={Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Wen and Dai, Ziqi and Tang, Jialong and Lin, Huan and Yang, Baosong and Xie, Pengjun and Huang, Fei and others}, booktitle={Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track}, pages={1393--1412}, year={2024} } ```