Instructions to use Alibaba-NLP/gte-base-en-v1.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Alibaba-NLP/gte-base-en-v1.5 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Alibaba-NLP/gte-base-en-v1.5", trust_remote_code=True, dtype="auto") - sentence-transformers
How to use Alibaba-NLP/gte-base-en-v1.5 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Alibaba-NLP/gte-base-en-v1.5", trust_remote_code=True) sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Transformers.js
How to use Alibaba-NLP/gte-base-en-v1.5 with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('sentence-similarity', 'Alibaba-NLP/gte-base-en-v1.5'); - Notebooks
- Google Colab
- Kaggle
model doesnt seem to support device_map="auto" for multi GPU .
model doesnt seem to support device_map="auto" for multi GPU . Please suggest.
Also adding more details for the error when we choose device_map="auto"
UNAVAILABLE: Internal: ValueError: NewModel does not support device_map='auto' | | | | . To implement support, the model class needs to implement the _no_split_modu | | | | les attribute.
This model can run efficiently on an 8GB GPU, and we did not consider multi-GPU scenarios.
You can enable xformers and unpadding to reduce GPU memory usage:
https://huggingface.co/Alibaba-NLP/new-impl#recommendation-enable-unpadding-and-acceleration-with-xformers