Add new SentenceTransformer model with an onnx backend
#12
by
gosshh
- opened
Hello!
This pull request has been automatically generated from the push_to_hub method from the Sentence Transformers library.
Full Model Architecture:
SentenceTransformer(
(0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: ORTModelForFeatureExtraction
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
(2): Dense({'in_features': 768, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
(3): Normalize()
)
Tip:
Consider testing this pull request before merging by loading the model from this PR with the revision argument:
from sentence_transformers import SentenceTransformer
# TODO: Fill in the PR number
pr_number = 2
model = SentenceTransformer(
"sentence-transformers/LaBSE",
revision=f"refs/pr/{pr_number}",
backend="onnx",
)
# Verify that everything works as expected
embeddings = model.encode(["The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium."])
print(embeddings.shape)
similarities = model.similarity(embeddings, embeddings)
print(similarities)
I have added the onnx optimized version of sentence-transformers/LaBSE model.
Hello!
I cherry-picked the models from this PR in https://huggingface.co/sentence-transformers/LaBSE/commit/ac91d6745aefb758c373ef4d37a13ff5e04ad876, as I'm wary about updating e.g. the config for a newer transformers version, as it might break for people on old versions.
Thanks a bunch, you should be able to do this now:
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("sentence-transformers/LaBSE", backend="onnx")
embeddings = model.encode(["The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium."])
print(embeddings.shape)
similarities = model.similarity(embeddings, embeddings)
print(similarities)
- Tom Aarsen
tomaarsen
changed pull request status to
closed