|
--- |
|
pipeline_tag: sentence-similarity |
|
tags: |
|
- feature-extraction |
|
- sentence-similarity |
|
language: en |
|
license: mit |
|
--- |
|
|
|
# ONNX Conversion of [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) |
|
|
|
- ONNX model for GPU with O4-O2 optimisation |
|
- We exported the model with `use_raw_attention_mask=True` [due to this issue](https://github.com/microsoft/onnxruntime/issues/18945) |
|
|
|
## Usage |
|
|
|
```python |
|
import torch.nn.functional as F |
|
from optimum.onnxruntime import ORTModelForFeatureExtraction |
|
from transformers import AutoTokenizer |
|
|
|
sentences = [ |
|
"The llama (/ˈlɑːmə/) (Lama glama) is a domesticated South American camelid.", |
|
"The alpaca (Lama pacos) is a species of South American camelid mammal.", |
|
"The vicuña (Lama vicugna) (/vɪˈkuːnjə/) is one of the two wild South American camelids.", |
|
] |
|
|
|
model_name = "EmbeddedLLM/bge-base-en-v1.5-onnx-o4-o2-gpu" |
|
device = "cuda" |
|
provider = "CUDAExecutionProvider" |
|
tokenizer = AutoTokenizer.from_pretrained(model_name) |
|
model = ORTModelForFeatureExtraction.from_pretrained( |
|
model_name, use_io_binding=True, provider=provider, device_map=device |
|
) |
|
inputs = tokenizer( |
|
sentences, |
|
padding=True, |
|
truncation=True, |
|
return_tensors="pt", |
|
max_length=model.config.max_position_embeddings, |
|
) |
|
inputs = inputs.to(device) |
|
embeddings = model(**inputs).last_hidden_state[:, 0] |
|
embeddings = F.normalize(embeddings, p=2, dim=1) |
|
print(embeddings.cpu().numpy().shape) |
|
``` |
|
|