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

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -1,3 +1,356 @@
----
-license: mit
----
+---
+language: 
+  - multilingual
+  - af
+  - am
+  - ar
+  - as
+  - az
+  - be
+  - bg
+  - bn
+  - br
+  - bs
+  - ca
+  - cs
+  - cy
+  - da
+  - de
+  - el
+  - en
+  - eo
+  - es
+  - et
+  - eu
+  - fa
+  - fi
+  - fr
+  - fy
+  - ga
+  - gd
+  - gl
+  - gu
+  - ha
+  - he
+  - hi
+  - hr
+  - hu
+  - hy
+  - id
+  - is
+  - it
+  - ja
+  - jv
+  - ka
+  - kk
+  - km
+  - kn
+  - ko
+  - ku
+  - ky
+  - la
+  - lo
+  - lt
+  - lv
+  - mg
+  - mk
+  - ml
+  - mn
+  - mr
+  - ms
+  - my
+  - ne
+  - nl
+  - 'no'
+  - om
+  - or
+  - pa
+  - pl
+  - ps
+  - pt
+  - ro
+  - ru
+  - sa
+  - sd
+  - si
+  - sk
+  - sl
+  - so
+  - sq
+  - sr
+  - su
+  - sv
+  - sw
+  - ta
+  - te
+  - th
+  - tl
+  - tr
+  - ug
+  - uk
+  - ur
+  - uz
+  - vi
+  - xh
+  - yi
+  - zh
+license: mit
+library_name: sentence-transformers
+tags:
+  - korean
+  - sentence-transformers
+  - transformers
+  - multilingual
+  - sentence-transformers
+  - sentence-similarity
+  - feature-extraction
+base_model: intfloat/multilingual-e5-large
+datasets: []
+metrics:
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
+widget:
+- source_sentence: 이집트 군대가 형제애를 단속하다
+  sentences:
+  - 이집트의 군대가 무슬림 형제애를 단속하다
+  - 아르헨티나의 기예르모 코리아와 네덜란드의 마틴 버커크의 또 다른 준결승전도 매력적이다.
+  - 그것이 사실일 수도 있다고 생각하는 것은 재미있다.
+- source_sentence: 오, 그리고 다시 결혼은 근본적인 인권이라고 주장한다.
+  sentences:
+  - 특히 결혼은 근본적인 인권이라고 말한 후에.
+  - 해변에 있는 흑인과 그의 개...
+  - 이란은 핵 프로그램이 평화적인 목적을 위한 것이라고 주장한다
+- source_sentence: 조지 샤힌은 안데르센 컨설팅 사업부에서 일했다.
+  sentences:
+  - 112건의 퇴거를 예방하거나 미연에 방지하여 151,619달러의 피난처 비용과 그들이 실향민이 되었을 때 가족들이 겪는 혼란을 덜어주었다.
+  - 안데르센 컨설팅은 여전히 번창하는 사업이다.
+  - 이것은 내가 영국의 아서 안데르센 사업부의 파트너인 짐 와디아를 아서 안데르센 경영진이 선택한 것보다 래리 웨인바흐를 안데르센 월드와이드의
+    경영 파트너로 승계하기 위해 안데르센 컨설팅 사업부(현재의 엑센츄어라고 알려져 있음)의 전 관리 파트너인 조지 샤힌에 대한 지지를 표명했을
+    때 가장 명백했다.
+- source_sentence: 그 표는 주요 경제 정보를 보여준다.
+  sentences:
+  - 표는 모집단 밀도를 나타냅니다.
+  - 아이들이 야외에서 놀고 있다.
+  - 표 3은 배출량 감소가 개인 소비와 국내총생산(GDP)의 다른 구성 요소에 미치는 영향을 비교하기 위해 2010년의 주요 거시경제 데이터를
+    요약한 것이다.
+- source_sentence: 안경을 쓴 나이든 남자가 바닥에 누워 갓난아기와 장난감 소방차를 가지고 놀고 있다.
+  sentences:
+  - 긴 검은 머리와 초록색 탱크톱을 가진 남자가 손가락을 보고 있다.
+  - 안경을 쓴 남자는 원숭이이고 아기 원숭이와 놀고 있다.
+  - 안경을 쓴 남자가 바닥에 누워 놀고 있다.
+pipeline_tag: sentence-similarity
+model-index:
+- name: upskyy/e5-large-korean
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev
+      type: sts-dev
+    metrics:
+    - type: pearson_cosine
+      value: 0.8710078333363093
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8698788475177747
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8598807479137434
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8682945370063891
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8596482760879562
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8679655812613122
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.8684600033706916
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.8668368265035578
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8710078333363093
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8698788475177747
+      name: Spearman Max
+---
+
+# upskyy/e5-large-korean
+
+This model is korsts and kornli finetuning model from [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large). It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) <!-- at revision ab10c1a7f42e74530fe7ae5be82e6d4f11a719eb -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 1024 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## Usage
+
+### Usage (Sentence-Transformers)
+
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("upskyy/e5-large-korean")
+
+# Run inference
+sentences = [
+    '아이를 가진 엄마가 해변을 걷는다.',
+    '두 사람이 해변을 걷는다.',
+    '한 남자가 해변에서 개를 산책시킨다.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+### Usage (HuggingFace Transformers)
+
+Without sentence-transformers, you can use the model like this: 
+First, you pass 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 = ["안녕하세요?", "한국어 문장 임베딩을 위한 버트 모델입니다."]
+
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained("upskyy/e5-large-korean")
+model = AutoModel.from_pretrained("upskyy/e5-large-korean")
+
+# 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.
+sentence_embeddings = mean_pooling(model_output, encoded_input["attention_mask"])
+
+print("Sentence embeddings:")
+print(sentence_embeddings)
+```
+
+
+## Evaluation
+
+### Metrics
+
+#### Semantic Similarity
+* Dataset: `sts-dev`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric             | Value      |
+| :----------------- | :--------- |
+| pearson_cosine     | 0.871      |
+| spearman_cosine    | 0.8699     |
+| pearson_manhattan  | 0.8599     |
+| spearman_manhattan | 0.8683     |
+| pearson_euclidean  | 0.8596     |
+| spearman_euclidean | 0.868      |
+| pearson_dot        | 0.8685     |
+| spearman_dot       | 0.8668     |
+| **pearson_max**    | **0.871**  |
+| **spearman_max**   | **0.8699** |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+
+### Framework Versions
+- Python: 3.10.13
+- Sentence Transformers: 3.0.1
+- Transformers: 4.42.4
+- PyTorch: 2.3.0+cu121
+- Accelerate: 0.30.1
+- Datasets: 2.16.1
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+
+```bibtex
+@article{wang2024multilingual,
+  title={Multilingual E5 Text Embeddings: A Technical Report},
+  author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Yang, Linjun and Majumder, Rangan and Wei, Furu},
+  journal={arXiv preprint arXiv:2402.05672},
+  year={2024}
+}
+```
+
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d85f779ad4259caa8459b18582d9682b45c622b5684bbb61c51863b30cff7184
+size 2239607176

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"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

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": 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 sha256:883b037111086fd4dfebbbc9b7cee11e1517b5e0c0514879478661440f137085
+size 17082987

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "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>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}