MoD-Embedding

from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F

tokenizer = AutoTokenizer.from_pretrained("bflhc/MoD-Embedding", padding_side='left')
model = AutoModel.from_pretrained("bflhc/MoD-Embedding")
model.eval()

def encode(texts):
    inputs = tokenizer(texts, padding=True, truncation=True,
                      max_length=8192, return_tensors="pt")

    with torch.no_grad():
        outputs = model(**inputs)
        # Use last token embedding
        embeddings = outputs.last_hidden_state[:, -1, :]
        # Normalize embeddings
        embeddings = F.normalize(embeddings, p=2, dim=1)

    return embeddings

# Example usage
texts = ["Hello world", "你好世界"]
embeddings = encode(texts)
similarity = torch.matmul(embeddings[0], embeddings[1])
print(f"Similarity: {similarity.item():.4f}")