Add exported ONNX model 'model_O2.onnx'
Browse filesHello!
*This pull request has been automatically generated from the [`export_optimized_onnx_model`](https://sbert.net/docs/package_reference/util.html#sentence_transformers.backend.export_optimized_onnx_model) function from the Sentence Transformers library.*
## Config
```python
OptimizationConfig(
optimization_level=2,
optimize_for_gpu=False,
fp16=False,
optimize_with_onnxruntime_only=None,
enable_transformers_specific_optimizations=True,
disable_gelu=None,
disable_gelu_fusion=False,
disable_layer_norm=None,
disable_layer_norm_fusion=False,
disable_attention=None,
disable_attention_fusion=False,
disable_skip_layer_norm=None,
disable_skip_layer_norm_fusion=False,
disable_bias_skip_layer_norm=None,
disable_bias_skip_layer_norm_fusion=False,
disable_bias_gelu=None,
disable_bias_gelu_fusion=False,
disable_embed_layer_norm=True,
disable_embed_layer_norm_fusion=True,
enable_gelu_approximation=False,
use_mask_index=False,
no_attention_mask=False,
disable_shape_inference=False,
use_multi_head_attention=False,
enable_gemm_fast_gelu_fusion=False,
use_raw_attention_mask=False,
disable_group_norm_fusion=True,
disable_packed_kv=True,
disable_rotary_embeddings=False
)
```
## Tip:
Consider testing this pull request before merging by loading the model from this PR with the `revision` argument:
```python
from sentence_transformers import SentenceTransformer
# TODO: Fill in the PR number
pr_number = 2
model = SentenceTransformer(
"tomaarsen/all-mpnet-base-v2",
revision=f"refs/pr/{pr_number}",
backend="onnx",
model_kwargs={"file_name": "onnx/model_O2.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)
```
- onnx/model_O2.onnx +3 -0
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14d01256f5f3d2245b15b596173bca4367c9405fde5700dd7fb4e110708c1793
|
3 |
+
size 435666661
|