初始化项目，由ModelHub XC社区提供模型

Model: NbAiLab/nb-sbert-base
Source: Original Platform

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false
+}

README.md

@@ -0,0 +1,242 @@
+---
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+datasets: NbAiLab/mnli-norwegian
+pipeline_tag: sentence-similarity
+widget:
+- source_sentence: This is a Norwegian boy
+  sentences:
+  - Dette er en norsk gutt
+  - This is an English boy
+  - This is a dog
+  example_title: Cross Language
+- source_sentence: Det er noen dyr utenfor vinduet
+  sentences:
+  - På utsiden kan jeg høre noen hunder
+  - Noen mennesker prater utenfor vinduet
+  - Alle burde ha kjæledyr
+  example_title: Paraphrases
+- source_sentence: En kvinne sitter i en stol
+  sentences:
+  - A woman is sitting in a chair
+  - Hun slapper av og leser i en bok
+  - Hun løper maraton
+  example_title: Paraphrases across language
+license: apache-2.0
+language:
+- 'no'
+---
+
+# NB-SBERT-BASE
+
+> [!NOTE]
+> As of April 13th 2026, there are now new versions of this model, with improved performance and increased context length.
+> - [NbAiLab/nb-sbert-v2-base](https://huggingface.co/NbAiLab/nb-sbert-v2-base)
+> - [NbAiLab/nb-sbert-v2-large](https://huggingface.co/NbAiLab/nb-sbert-v2-large)
+
+NB-SBERT-BASE is a [SentenceTransformers](https://www.SBERT.net) model trained on a [machine translated version of the MNLI dataset](https://huggingface.co/datasets/NbAiLab/mnli-norwegian), starting from [nb-bert-base](https://huggingface.co/NbAiLab/nb-bert-base). 
+
+The model maps sentences & paragraphs to a 768 dimensional dense vector space. This vector can be used for tasks like clustering and semantic search. Below we give some examples on how to use the model. The easiest way is to simply measure the cosine distance between two sentences. Sentences that are close to each other in meaning, will have a small cosine distance and a similarity close to 1. The model is trained in such a way that similar sentences in different languages should also be close to each other. Ideally, an English-Norwegian sentence pair should have high similarity.
+
+## Embeddings and Sentence Similarity (Sentence-Transformers)
+
+As seen above, using the library [sentence-transformers](https://www.SBERT.net) makes the use of these models quite convenient:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can use the model like this:
+
+```python
+from sentence_transformers import SentenceTransformer, util
+sentences = ["This is a Norwegian boy", "Dette er en norsk gutt"]
+
+model = SentenceTransformer('NbAiLab/nb-sbert-base')
+embeddings = model.encode(sentences)
+print(embeddings)
+
+# Compute cosine-similarities with sentence transformers
+cosine_scores = util.cos_sim(embeddings[0],embeddings[1])
+print(cosine_scores)
+
+# Compute cosine-similarities with SciPy
+from scipy import spatial
+scipy_cosine_scores = 1 - spatial.distance.cosine(embeddings[0],embeddings[1])
+print(scipy_cosine_scores)
+
+# Both should give 0.8250 in the example above.
+
+```
+
+
+## Embeddings and Sentence Similarity (HuggingFace Transformers)
+Without [sentence-transformers](https://www.SBERT.net), you can still use the model. First, you pass in your input through the transformer model, then you have to apply the right pooling-operation on top of the contextualized word embeddings.
+
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+
+#Mean Pooling - Take attention mask into account for correct averaging
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+
+
+# Sentences we want sentence embeddings for
+sentences = ["This is a Norwegian boy", "Dette er en norsk gutt"]
+
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained('NbAiLab/nb-sbert-base')
+model = AutoModel.from_pretrained('NbAiLab/nb-sbert-base')
+
+# Tokenize sentences
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+
+# Compute token embeddings
+with torch.no_grad():
+    model_output = model(**encoded_input)
+
+# Perform pooling. In this case, mean pooling.
+embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+
+print(embeddings)
+
+# Compute cosine-similarities with SciPy
+from scipy import spatial
+scipy_cosine_scores = 1 - spatial.distance.cosine(embeddings[0],embeddings[1])
+print(scipy_cosine_scores)
+
+# This should give 0.8250 in the example above.
+
+```
+## SetFit - Few Shot Classification
+[SetFit](https://github.com/huggingface/setfit) is a method for using sentence-transformers to solve one of major problem that all NLP researchers are facing: Too few labeled training examples. The 'nb-sbert-base' can be plugged directly into the SetFit library. Please see [this tutorial](https://huggingface.co/blog/setfit) for how to use this technique.
+
+
+## Keyword Extraction
+The model can be used for extracting keywords from text. The basic technique is to find the words that are most similar to the document. There are various frameworks for doing this. An easy way is to use [KeyBERT](https://github.com/MaartenGr/KeyBERT). This example shows how this can be done.
+
+```bash
+pip install keybert
+```
+
+```python
+from keybert import KeyBERT
+from sentence_transformers import SentenceTransformer
+sentence_model = SentenceTransformer("NbAiLab/nb-sbert-base")
+kw_model = KeyBERT(model=sentence_model)
+
+doc = """
+De første nasjonale bibliotek har sin opprinnelse i kongelige samlinger eller en annen framstående myndighet eller statsoverhode. 
+Et av de første planene for et nasjonalbibliotek i England ble fremmet av den walisiske matematikeren og mystikeren John Dee som 
+i 1556 presenterte en visjonær plan om et nasjonalt bibliotek for gamle bøker, manuskripter og opptegnelser for dronning Maria I 
+av England. Hans forslag ble ikke tatt til følge.
+"""
+kw_model.extract_keywords(doc, stop_words=None)
+
+# [('nasjonalbibliotek', 0.5242), ('bibliotek', 0.4342), ('samlinger', 0.3334), ('statsoverhode', 0.33), ('manuskripter', 0.3061)]
+```
+
+The [KeyBERT homepage](https://github.com/MaartenGr/KeyBERT) provides other several interesting examples: combining KeyBERT with stop words, extracting longer phrases, or directly producing highlighted text.
+
+## Topic Modeling
+To analyse a group of documents and determine the topics, has a lot of use cases. [BERTopic](https://github.com/MaartenGr/BERTopic) combines the power of sentence transformers with c-TF-IDF to create clusters for easily interpretable topics.
+
+It would take too much time to explain topic modeling here. Instead we recommend that you take a look at the link above, as well as the [documentation](https://maartengr.github.io/BERTopic/index.html). The main adaptation you would need to do to use the Norwegian nb-sbert-base, is to add the following:
+
+```python
+topic_model = BERTopic(embedding_model='NbAiLab/nb-sbert-base').fit(docs)
+```
+
+## Similarity Search
+Another common use case for a SentenceTransformers model is to find relevant documents or passages of documents given a certain query text. In this scenario, it is pretty common to have a vector database that stores the embedding vectors for all our documents. Then, at runtime, an embedding for the query text is generated and compared efficiently against the vector database.
+
+While production vector databases exist, a quick way to experiment with them is by using [`autofaiss`](https://github.com/criteo/autofaiss):
+
+```bash
+pip install autofaiss sentence-transformers
+```
+
+```python
+from autofaiss import build_index
+import numpy as np
+
+from sentence_transformers import SentenceTransformer, util
+sentences = ["This is a Norwegian boy", "Dette er en norsk gutt", "A red house"]
+
+model = SentenceTransformer('NbAiLab/nb-sbert-base')
+embeddings = model.encode(sentences)
+index, index_infos = build_index(embeddings, save_on_disk=False)
+
+# Search for the closest matches
+query = model.encode(["A young boy"])
+_, index_matches = index.search(query, 1)
+print(index_matches)
+```
+
+
+
+
+# Evaluation and Parameters
+
+## Evaluation
+Evaluation results on the sts-test dataset:
+|                        | Pearson    | Spearman   |
+|------------------------|------------|------------|
+| Cosine Similarity      | **0.8275** | **0.8245** |
+| Manhattan Distance     | 0.8193     | 0.8182     |
+| Euclidean Distance     | 0.8190     | 0.8180     |
+| Dot Product Similarity | 0.8039     | 0.7951     |
+
+## Training
+The model was trained with the parameters:
+
+**DataLoader**:
+
+`sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader` of length 16471 with parameters:
+```
+{'batch_size': 32}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
+  ```
+  {'scale': 20.0, 'similarity_fct': 'cos_sim'}
+  ```
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 1,
+    "evaluation_steps": 1647,
+    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
+    "optimizer_params": {
+        "lr": 2e-05
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 1648,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 75, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
+)
+```
+
+## Citing & Authors
+The model was trained by Rolv-Arild Braaten and Per Egil Kummervold. Documentation written by Javier de la Rosa, Rov-Arild Braaten and Per Egil Kummervold.

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "NbAiLab/nb-bert-base",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.20.0",
+    "pytorch": "1.11.0+cu113"
+  }
+}

eval/similarity_evaluation_sts-dev_results.csv

@@ -0,0 +1,12 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,1647,0.823375587514228,0.8265825704334538,0.8273972164909515,0.8292214672723786,0.8268840482871875,0.8283000360315067,0.8022955514671963,0.8006369955886341
+0,3294,0.8318956230225233,0.8340475951581009,0.8349323944058863,0.835464435993529,0.8345877379588028,0.834995629472717,0.8103564960851812,0.8066427524023101
+0,4941,0.828103495909552,0.831719114903505,0.8292618436661121,0.8318879068349369,0.8289486077904916,0.8315578247566098,0.8080373423735806,0.8069119429795405
+0,6588,0.8256351268185107,0.8299253289680852,0.8287684115268311,0.830869096523304,0.8290049577465493,0.8311304472374726,0.8009607820136238,0.7986429675221425
+0,8235,0.8235746706117698,0.8264818265916876,0.826661103205969,0.8295939052518218,0.8265861275744042,0.8294574834494906,0.7993636707446155,0.7966738647397561
+0,9882,0.8333018947237008,0.8353349127724712,0.8336345633856252,0.8368681832577541,0.8340102013902385,0.8374881829417399,0.8086112939096168,0.8058078425734608
+0,11529,0.833741268658269,0.8363397426474096,0.8301428078897971,0.8335788510623737,0.8300640056874611,0.8334126079162164,0.813440371609937,0.8114798251354435
+0,13176,0.8303966197645557,0.8327355088433634,0.830594023192226,0.8340560293276226,0.8304148121939335,0.8338880327704051,0.8058855480985928,0.8035656381791165
+0,14823,0.834921212698747,0.8369408800729372,0.833990310947668,0.8374576330985931,0.8337706796275132,0.8372014318541703,0.8136963551460357,0.8112018516340024
+0,16470,0.8382865802719606,0.8397542610180401,0.8352120088313325,0.8390880986366062,0.8350079932947272,0.8387915325956439,0.8176968683400706,0.8152200305635741
+0,-1,0.8382865920818949,0.8397542610180401,0.835212018493872,0.8390880986366062,0.8350080052606882,0.8387915325956439,0.8176968836585897,0.8152200305635741

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:542120491898049bda60a6e83ef8ff17e1e9366f3562a5bfc1715efaacdb9668
+size 711440320

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6ff8649a20f3d7379d927298b15d08ec88a2c7dc76a5948a3ff4cffe2842f12
+size 711483185

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 75,
+  "do_lower_case": false
+}

similarity_evaluation_sts-test_results.csv

@@ -0,0 +1,2 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+-1,-1,0.8275085075461329,0.82454653044575,0.8189631397786282,0.8179737003889682,0.8192793931752765,0.8181757117136191,0.8038510401130279,0.7950975162189595

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "name_or_path": "NbAiLab/nb-bert-base",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}