Feature Extraction
Transformers
PyTorch
Safetensors
English
bert
mteb
sentence-transfomres
Eval Results (legacy)
text-embeddings-inference
Instructions to use BAAI/bge-large-en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BAAI/bge-large-en with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="BAAI/bge-large-en")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("BAAI/bge-large-en") model = AutoModel.from_pretrained("BAAI/bge-large-en") - Inference
- Notebooks
- Google Colab
- Kaggle
How to set the max length from 512 to 2048?
#11
by kk3dmax - opened
How to set the max length from 512 to 2048?
embed_model.client.max_seq_length = 2048 is what I found, not sure is it correct.
The max length for bge is limited to 512. For sentences whose length is larger than 512, it will process only the first 512 tokens.
Therefore, setting the max_seq_length has no effect. We suggest splitting the long document into several passages.
ok, thanks for your clairify.