Upload folder using huggingface_hub

.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 +1,113 @@
+---
+license: mit
+language:
+- en
+license_link: https://github.com/FlagOpen/FlagEmbedding/blob/master/LICENSE
+base_model: 
+  - BAAI/bge-reranker-base
+---
+# bge-reranker-base-int8-ov
+ * Model creator: [BAAI](https://huggingface.co/BAAI)
+ * Original model: [bge-reranker-base](https://huggingface.co/BAAI/bge-reranker-base)
+
+## Description
+This is [bge-reranker-base](https://huggingface.co/BAAI/bge-reranker-base) model converted to the [OpenVINO™ IR](https://docs.openvino.ai/2025/documentation/openvino-ir-format.html) (Intermediate Representation) format with quantization to INT8 by [NNCF](https://github.com/openvinotoolkit/nncf).
+
+**Disclaimer**: Model is provided as a preview and may be update in the future.
+
+## Quantization Parameters
+
+The quantization was performed using the next code:
+
+```
+from functools import partial
+
+from transformers import AutoTokenizer
+
+from optimum.intel import OVConfig, OVModelForSequenceClassification, OVQuantizationConfig, OVQuantizer
+
+
+MODEL_ID = "OpenVINO/bge-reranker-base-fp16-ov"
+base_model_path = "bge-reranker-base-fp16-ov"
+int8_ptq_model_path = "bge-reranker-base-int8"
+
+model = OVModelForSequenceClassification.from_pretrained(MODEL_ID)
+model.save_pretrained(base_model_path)
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+tokenizer.save_pretrained(base_model_path)
+
+
+quantizer = OVQuantizer.from_pretrained(model)
+
+def preprocess_function(examples, tokenizer):
+    return tokenizer(examples["sentence"], padding="max_length", max_length=384, truncation=True)
+
+
+calibration_dataset = quantizer.get_calibration_dataset(
+    "glue",
+    dataset_config_name="sst2",
+    preprocess_function=partial(preprocess_function, tokenizer=tokenizer),
+    num_samples=300,
+    dataset_split="train",
+)
+
+ov_config = OVConfig(quantization_config=OVQuantizationConfig())
+
+quantizer.quantize(ov_config=ov_config, calibration_dataset=calibration_dataset, save_directory=int8_ptq_model_path)
+tokenizer.save_pretrained(int8_ptq_model_path)
+```
+
+For more information on quantization, check the [OpenVINO model optimization guide](https://docs.openvino.ai/2025/openvino-workflow/model-optimization-guide/quantizing-models-post-training.html).
+
+
+## Compatibility
+
+The provided OpenVINO™ IR model is compatible with:
+
+* OpenVINO version 2025.1.0 and higher
+* Optimum Intel 1.24.0 and higher
+
+
+## Running Model Inference with [Optimum Intel](https://huggingface.co/docs/optimum/intel/index)
+
+1. Install packages required for using [Optimum Intel](https://huggingface.co/docs/optimum/intel/index) integration with the OpenVINO backend:
+
+```
+pip install optimum[openvino]
+```
+
+2. Run model inference:
+
+```
+from transformers import AutoTokenizer
+from optimum.intel import OVModelForSequenceClassification
+
+
+tokenizer = AutoTokenizer.from_pretrained('OpenVINO/bge-reranker-base-int8-ov')
+model = OVModelForSequenceClassification.from_pretrained('OpenVINO/bge-reranker-base-int8-ov')
+
+pairs = [['what is panda?', 'hi'], ['what is panda?', 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.']]
+
+inputs = tokenizer(pairs, padding=True, truncation=True, return_tensors='pt', max_length=512)
+scores = model(**inputs, return_dict=True).logits.view(-1, ).float()
+print(scores)
+```
+
+For more examples and possible optimizations, refer to the [Inference with Optimum Intel](https://docs.openvino.ai/2025/openvino-workflow-generative/inference-with-optimum-intel.html).
+
+You can find more detailed usage examples in OpenVINO Notebooks:
+
+- [RAG text generation](https://openvinotoolkit.github.io/openvino_notebooks/?search=RAG+system)
+
+## Limitations
+
+Check the original [model card](https://huggingface.co/BAAI/bge-reranker-base) for limitations.
+
+## Legal information
+
+The original model is distributed under [MIT](https://github.com/FlagOpen/FlagEmbedding/blob/master/LICENSE) license. More details can be found in [bge-reranker-base](https://huggingface.co/BAAI/bge-reranker-base).
+
+## Disclaimer
+
+Intel is committed to respecting human rights and avoiding causing or contributing to adverse impacts on human rights. See [Intel’s Global Human Rights Principles](https://www.intel.com/content/dam/www/central-libraries/us/en/documents/policy-human-rights.pdf). Intel’s products and software are intended only to be used in applications that do not cause or contribute to adverse impacts on human rights.

config.json

@@ -0,0 +1,34 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "OpenVINO/bge-reranker-base-fp16-ov",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.48.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

openvino_config.json

@@ -0,0 +1,24 @@
+{
+  "compression": null,
+  "dtype": "int8",
+  "input_info": null,
+  "optimum_version": "1.24.0",
+  "quantization_config": {
+    "activation_format": "int8",
+    "bits": 8,
+    "dataset": null,
+    "fast_bias_correction": true,
+    "ignored_scope": null,
+    "model_type": "transformer",
+    "num_samples": 300,
+    "overflow_fix": "disable",
+    "processor": null,
+    "smooth_quant_alpha": null,
+    "sym": false,
+    "tokenizer": null,
+    "trust_remote_code": false,
+    "weight_format": "int8"
+  },
+  "save_onnx_model": false,
+  "transformers_version": "4.48.3"
+}

openvino_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dcc0aa449397a94037eab006108cfb03f8cb77745d87fbfe7601e4f20d3ee38
+size 280016732

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

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": true,
+    "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 sha256:6465c7619e715f898f06ed509f45338b915939321afa048f48a7c8ac9ee875a0
+size 17083063

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": true,
+      "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>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}