liuyanyi/bge-m3-hf

BGE-M3 in HuggingFace Transformer

This is not an official implementation of BGE-M3. Official implementation can be found in Flag Embedding project.

Introduction

Full introduction please see the github repo.

https://github.com/liuyanyi/transformers-bge-m3

Use BGE-M3 in HuggingFace Transformer

from transformers import AutoModel, AutoTokenizer

# Trust remote code is required to load the model
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
model = AutoModel.from_pretrained(model_path, trust_remote_code=True)

input_str = "Hello, world!"
input_ids = tokenizer(input_str, return_tensors="pt", padding=True, truncation=True)

output = model(**input_ids, return_dict=True)

dense_output = output.dense_output # To align with Flag Embedding project, a normalization is required
colbert_output = output.colbert_output # To align with Flag Embedding project, a normalization is required
sparse_output = output.sparse_output

References

• Official BGE-M3 Weight
• Flag Embedding
• HuggingFace Transformer