Upload ONNX opset 14 model with int8 quantization

.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 +1,93 @@
+---
+language: multilingual
+license: mit
+tags:
+  - onnx
+  - optimum
+  - quantized
+  - int8
+  - text-embedding
+  - onnxruntime
+  - opset14
+  - text-classification
+  - gpu
+  - optimized
+datasets:
+  - mmarco
+pipeline_tag: sentence-similarity
+---
+
+# gte-multilingual-reranker-base-onnx-op14-opt-gpu-int8-quantized
+
+This model is a quantized ONNX version of [Alibaba-NLP/gte-multilingual-reranker-base](https://huggingface.co/Alibaba-NLP/gte-multilingual-reranker-base) using ONNX opset 14.
+
+## Model Details
+
+- **Quantization Type**: INT8
+- **ONNX Opset**: 14
+- **Task**: text-classification
+- **Target Device**: GPU
+- **Optimized**: Yes
+- **Framework**: ONNX Runtime
+- **Original Model**: [Alibaba-NLP/gte-multilingual-reranker-base](https://huggingface.co/Alibaba-NLP/gte-multilingual-reranker-base)
+- **Quantized On**: 2025-03-27
+
+## 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("quantized_model")
+tokenizer = AutoTokenizer.from_pretrained("quantized_model")
+
+# Prepare input
+text = "Your text here"
+inputs = tokenizer(text, return_tensors="pt")
+
+# Run inference
+outputs = model(**inputs)
+```
+
+## Quantization Process
+
+This model was quantized using ONNX Runtime with int8 quantization.
+The quantization was performed using the Optimum library from Hugging Face with opset 14.
+Graph optimization was applied during export, targeting GPU devices.
+
+
+## Performance Comparison
+
+Quantized models generally offer better inference speed with a slight trade-off in accuracy.
+This INT8 quantized model should provide significantly faster inference than the original model.

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:b1fa8e49af1e77c9679b5a647bfa924629674891e43daf4bb9d7f86a6c9f65cf
+size 917138575

quantization_report.json

@@ -0,0 +1,15 @@
+{
+  "technique": "int8",
+  "success": true,
+  "fallback_used": false,
+  "details": {
+    "precision": "int8",
+    "per_channel": true,
+    "reduce_range": false,
+    "op_types": [
+      "MatMul",
+      "Add",
+      "Conv"
+    ]
+  }
+}

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>"
+}