Add new SentenceTransformer model with an onnx backend

Hello!

*This pull request has been automatically generated from the [`push_to_hub`](https://sbert.net/docs/package_reference/sentence_transformer/SentenceTransformer.html#sentence_transformers.SentenceTransformer.push_to_hub) method from the Sentence Transformers library.*

## Full Model Architecture:
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 8192, '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): Normalize()
)
```

## 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(
"louisbrulenaudet/lemone-embed-pro",
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)
```

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "Alibaba-NLP/gte-multilingual-base",
   "architectures": [
     "NewModel"
   ],
@@ -42,7 +41,7 @@
   },
   "rope_theta": 20000,
   "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
+  "transformers_version": "4.52.4",
   "type_vocab_size": 1,
   "unpad_inputs": false,
   "use_memory_efficient_attention": false,

config_sentence_transformers.json

@@ -1,10 +1,10 @@
 {
   "__version__": {
-    "sentence_transformers": "3.1.1",
-    "transformers": "4.44.2",
-    "pytorch": "2.3.0+cu121"
+    "sentence_transformers": "4.1.0",
+    "transformers": "4.52.4",
+    "pytorch": "2.7.1"
   },
   "prompts": {},
   "default_prompt_name": null,
-  "similarity_fn_name": null
+  "similarity_fn_name": "cosine"
 }

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99edaba2b8e2476a74ab359cd2d7c3faa63ada106fd5043449f32dfb441d834e
+size 1255519330

tokenizer_config.json

@@ -45,10 +45,18 @@
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
   "eos_token": "</s>",
+  "extra_special_tokens": {},
   "mask_token": "<mask>",
+  "max_length": 8192,
   "model_max_length": 8192,
+  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "</s>",
-  "tokenizer_class": "XLMRobertaTokenizer",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }