Upload folder using huggingface_hub

README.md

@@ -0,0 +1,124 @@
+---
+license: mit
+language:
+- en
+license_link: https://github.com/FlagOpen/FlagEmbedding/blob/master/LICENSE
+base_model: 
+  - BAAI/bge-base-en-v1.5
+---
+# bge-base-en-v1.5-int8-ov
+ * Model creator: [BAAI](https://huggingface.co/BAAI)
+ * Original model: [bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5)
+
+## Description
+This is [bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) 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, OVModelForFeatureExtraction, OVQuantizationConfig, OVQuantizer
+
+
+MODEL_ID = "OpenVINO/bge-base-en-v1.5-fp16-ov"
+base_model_path = "bge-base-en-v1.5"
+int8_ptq_model_path = "bge-base-en-v1.5-int8"
+
+model = OVModelForFeatureExtraction.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/2024/openvino-workflow/model-optimization-guide/weight-compression.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 "langchain-community>=0.2.15" optimum[openvino] huggingface_hub
+```
+
+2. Run model inference:
+
+```
+from langchain_community.embeddings import OpenVINOBgeEmbeddings
+
+
+embedding_model_name = 'OpenVINO/bge-base-en-v1.5-int8-ov'
+embedding_model_kwargs = {"device": "CPU", "compile": False}
+encode_kwargs = {
+    "mean_pooling": False,
+    "normalize_embeddings": True,
+    "batch_size": 4,
+}
+
+embedding = OpenVINOBgeEmbeddings(
+    model_name_or_path=embedding_model_name,
+    model_kwargs=embedding_model_kwargs,
+    encode_kwargs=encode_kwargs,
+)
+
+embedding.ov_model.compile()
+
+text = "This is a test document."
+embedding_result = embedding.embed_query(text)
+embedding_result[:3]
+```
+
+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-base-en-v1.5) 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-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5).
+
+## 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 +1,33 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "OpenVINO/bge-base-en-v1.5-fp16-ov",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "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,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

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:e93dee628b35680e54242ee38e96d5c6cd9d1e5ad8f065f0c4cc36c8744cf2fa
+size 109974480

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}