Upload folder using huggingface_hub

README.md

@@ -1,3 +1,65 @@
----
-license: apache-2.0
----
+---
+library_name: transformers.js
+base_model: NbAiLab/nb-sbert-base
+tags:
+- onnx
+- transformers.js
+- feature-extraction
+- sentence-similarity
+language:
+- no
+pipeline_tag: feature-extraction
+license: apache-2.0
+---
+
+# ONNX version of NbAiLab/nb-sbert-base
+
+This repository contains **ONNX-converted weights** for [NbAiLab/nb-sbert-base](https://huggingface.co/NbAiLab/nb-sbert-base), compatible with [Transformers.js](https://huggingface.co/docs/transformers.js).
+
+It includes both:
+1.  **Quantized (int8):** Faster, smaller (default).
+2.  **Full Precision (float32):** Higher theoretical accuracy, larger file size.
+
+## Usage (Node.js)
+
+First, install the library:
+
+```bash
+npm install @huggingface/transformers
+```
+
+## Option 1: Use Quantized Model (Recommended)
+This is the default behavior. It loads model_quantized.onnx (approx. 4x smaller).
+
+```javascript
+import { pipeline } from '@huggingface/transformers';
+
+const embedder = await pipeline(
+  'feature-extraction', 
+  'lebchen/nb-sbert-base-onnx', 
+  { device: 'auto' } // Defaults to { quantized: true }
+);
+
+const output = await embedder("Dette er en test.", { pooling: 'mean', normalize: true });
+```
+
+## Option 2: Use Full Precision Model
+
+```
+import { pipeline } from '@huggingface/transformers';
+
+const embedder = await pipeline(
+  'feature-extraction', 
+  'lebchen/nb-sbert-base-onnx', 
+  { 
+    device: 'auto', 
+    quantized: false // Forces loading of model.onnx
+  }
+);
+```
+
+## Credits & License
+
+The original model was developed by the National Library of Norway (AI Lab). Original repository: https://huggingface.co/NbAiLab/nb-sbert-base
+
+This distribution is licensed under Apache 2.0.

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "dtype": "float32",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.6",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e24f45ee328e59f55b9b02e2f989e3eb6056d47d5e7ea86e8e62e2d97be40372
+size 709244796

model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1af59580c3333e46563ecd5c34ad5dcfc2544dec01df547a9af63412459a4342
+size 178440396

ort_config.json

@@ -0,0 +1,33 @@
+{
+  "one_external_file": true,
+  "opset": null,
+  "optimization": {},
+  "quantization": {
+    "activations_dtype": "QUInt8",
+    "activations_symmetric": false,
+    "format": "QOperator",
+    "is_static": false,
+    "mode": "IntegerOps",
+    "nodes_to_exclude": [],
+    "nodes_to_quantize": [],
+    "operators_to_quantize": [
+      "Conv",
+      "MatMul",
+      "Attention",
+      "LSTM",
+      "Gather",
+      "Transpose",
+      "EmbedLayerNormalization"
+    ],
+    "per_channel": true,
+    "qdq_add_pair_to_weight": false,
+    "qdq_dedicated_pair": false,
+    "qdq_op_type_per_channel_support_to_axis": {
+      "MatMul": 1
+    },
+    "reduce_range": false,
+    "weights_dtype": "QInt8",
+    "weights_symmetric": true
+  },
+  "use_external_data_format": false
+}

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 +1,65 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 75,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}