Sentence Similarity
sentence-transformers
PyTorch
ONNX
Safetensors
OpenVINO
English
bert
mteb
Sentence Transformers
Eval Results (legacy)
text-embeddings-inference
Instructions to use thenlper/gte-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use thenlper/gte-base with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("thenlper/gte-base") 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] - Inference
- Notebooks
- Google Colab
- Kaggle
Device Map Auto not supported and Is there any way to increase the length of input sequence ????
#5
by ideepankarsharma2003 - opened
Is there any way to increase the length of the input sequence?
This checkpoint is initialized from BertModel, which uses absolute position embeddings and restricts the length to 512. I have noticed that some people have proposed methods for expanding the input length, please refer to https://huggingface.co/thenlper/gte-large/discussions/9
