Upload ONNX model with opset 19

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,88 @@
+---
+language: multilingual
+license: mit
+tags:
+  - onnx
+  - optimum
+  - text-embedding
+  - onnxruntime
+  - opset19
+  - sentence-similarity
+  - gpu
+  - optimized
+datasets:
+  - mmarco
+pipeline_tag: sentence-similarity
+---
+
+# gte-multilingual-reranker-base-onnx-op19-opt-gpu
+
+This model is an ONNX version of [Alibaba-NLP/gte-multilingual-reranker-base](https://huggingface.co/Alibaba-NLP/gte-multilingual-reranker-base) using ONNX opset 19.
+
+## Model Details
+
+- **Framework**: ONNX Runtime
+- **ONNX Opset**: 19
+- **Task**: sentence-similarity
+- **Target Device**: GPU
+- **Optimized**: Yes
+- **Original Model**: [Alibaba-NLP/gte-multilingual-reranker-base](https://huggingface.co/Alibaba-NLP/gte-multilingual-reranker-base)
+- **Exported On**: 2025-03-31
+
+## Environment and Package Versions
+
+| Package | Version |
+| --- | --- |
+| transformers | 4.48.3 |
+| optimum | 1.24.0 |
+| onnx | 1.17.0 |
+| onnxruntime | 1.21.0 |
+| torch | 2.5.1 |
+| numpy | 1.26.4 |
+| huggingface_hub | 0.28.1 |
+| python | 3.12.9 |
+| system | Darwin 24.3.0 |
+
+
+### Applied Optimizations
+
+| Optimization | Setting |
+| --- | --- |
+| Graph Optimization Level | Extended |
+| Optimize for GPU | Yes |
+| Use FP16 | No |
+| Transformers Specific Optimizations Enabled | Yes |
+| Gelu Fusion Enabled | Yes |
+| Layer Norm Fusion Enabled | Yes |
+| Attention Fusion Enabled | Yes |
+| Skip Layer Norm Fusion Enabled | Yes |
+| Gelu Approximation Enabled | Yes |
+
+
+## Usage
+
+```python
+from optimum.onnxruntime import ORTModelForSequenceClassification
+from transformers import AutoTokenizer
+
+# Load model and tokenizer
+model = ORTModelForSequenceClassification.from_pretrained("onnx")
+tokenizer = AutoTokenizer.from_pretrained("onnx")
+
+# Prepare input
+text = "Your text here"
+inputs = tokenizer(text, return_tensors="pt")
+
+# Run inference
+outputs = model(**inputs)
+```
+
+## Export Process
+
+This model was exported to ONNX format using the Optimum library from Hugging Face with opset 19.
+Graph optimization was applied during export, targeting GPU devices.
+
+## Performance
+
+ONNX Runtime models generally offer better inference speed compared to native PyTorch models,
+especially when deployed to production environments.

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "Alibaba-NLP/gte-multilingual-reranker-base",
+  "architectures": [
+    "NewForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig",
+    "AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel",
+    "AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM",
+    "AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice",
+    "AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering",
+    "AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification",
+    "AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification"
+  },
+  "classifier_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "layer_norm_type": "layer_norm",
+  "logn_attention_clip1": false,
+  "logn_attention_scale": false,
+  "max_position_embeddings": 8192,
+  "model_type": "new",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pack_qkv": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "rope",
+  "rope_scaling": {
+    "factor": 8.0,
+    "type": "ntk"
+  },
+  "rope_theta": 20000,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "type_vocab_size": 1,
+  "unpad_inputs": false,
+  "use_memory_efficient_attention": false,
+  "vocab_size": 250048
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:674ae753bf4d9f266b3ff83a68e6cfb3aea969d1bc79cba078d068bd4c75654e
+size 1257788813

optimization_report.json

@@ -0,0 +1,18 @@
+{
+  "successful_optimizations": {
+    "optimization_level": 2,
+    "optimize_for_gpu": true,
+    "fp16": false,
+    "enable_transformers_specific_optimizations": true,
+    "gelu_fusion_enabled": true,
+    "layer_norm_fusion_enabled": true,
+    "attention_fusion_enabled": true,
+    "skip_layer_norm_fusion_enabled": true,
+    "gelu_approximation_enabled": true
+  },
+  "failed_optimizations": {},
+  "model_name": "Alibaba-NLP/gte-multilingual-reranker-base",
+  "task": "sentence-similarity",
+  "target_device": "GPU",
+  "timestamp": "2025-03-31T13:12:13.084323"
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 32768,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

upload_info.json

@@ -0,0 +1,6 @@
+{
+  "hf_repo": "JustJaro/gte-multilingual-reranker-base-onnx-op14-opt-gpu",
+  "upload_date": "2025-03-27T17:40:50.247074",
+  "upload_success": true,
+  "model_url": "https://huggingface.co/JustJaro/gte-multilingual-reranker-base-onnx-op14-opt-gpu"
+}