app.py

from torch import Tensor, nn
from transformers import CLIPTextModel, CLIPTokenizer, T5EncoderModel, T5Tokenizer


class HFEmbedder(nn.Module):
    def __init__(self, version: str, max_length: int, **hf_kwargs):
        super().__init__()
        self.is_clip = version.startswith("openai")
        self.max_length = max_length
        self.output_key = "pooler_output" if self.is_clip else "last_hidden_state"

        if self.is_clip:
            self.tokenizer: CLIPTokenizer = CLIPTokenizer.from_pretrained(version, max_length=max_length)
            self.hf_module: CLIPTextModel = CLIPTextModel.from_pretrained(version, **hf_kwargs)
        else:
            self.tokenizer: T5Tokenizer = T5Tokenizer.from_pretrained(version, max_length=max_length)
            self.hf_module: T5EncoderModel = T5EncoderModel.from_pretrained(version, **hf_kwargs)

        self.hf_module = self.hf_module.eval().requires_grad_(False)

    def forward(self, text: list[str]) -> Tensor:
        batch_encoding = self.tokenizer(
            text,
            truncation=True,
            max_length=self.max_length,
            return_length=False,
            return_overflowing_tokens=False,
            padding="max_length",
            return_tensors="pt",
        )

        outputs = self.hf_module(
            input_ids=batch_encoding["input_ids"].to(self.hf_module.device),
            attention_mask=None,
            output_hidden_states=False,
        )
        return outputs[self.output_key]


def load_t5(device: str | torch.device = "cuda", max_length: int = 512) -> HFEmbedder:
    # max length 64, 128, 256 and 512 should work (if your sequence is short enough)
    return HFEmbedder("google/t5-v1_1-xxl", max_length=max_length, torch_dtype=torch.bfloat16).to(device)

if __name__ == "__main__":
    device = "cuda" if torch.cuda.is_available() else "cpu"
    t5 = load_t5(device, max_length=256)
    texts = ["这是一个测试句子。"]
    embeddings = t5(texts)
    print(f"Embeddings shape: {embeddings.shape}")