init

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 +1,173 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+  - sentence-transformers
+  - feature-extraction
+  - sentence-similarity
+  - transformers
+language: ko
+
+---
+
+# kf-deberta-multitask
+
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. You can check the training recipes on [GitHub](https://github.com/upskyy/kf-deberta-multitask).
+
+<!--- Describe your model here -->
+
+## Usage (Sentence-Transformers)
+
+Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+
+```
+pip install -U sentence-transformers
+```
+
+Then you can use the model like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+sentences = ["안녕하세요?", "한국어 문장 임베딩을 위한 버트 모델입니다."]
+
+model = SentenceTransformer("upskyy/kf-deberta-multitask")
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+## Usage (HuggingFace Transformers)
+
+Without [sentence-transformers](https://www.SBERT.net), 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/kf-deberta-multitask")
+model = AutoModel.from_pretrained("upskyy/kf-deberta-multitask")
+
+# 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 Results
+
+<!--- Describe how your model was evaluated -->
+
+KorSTS, KorNLI 학습 데이터셋으로 멀티 태스크 학습을 진행한 후 KorSTS 평가 데이터셋으로 평가한 결과입니다.
+
+- Cosine Pearson: 85.75
+- Cosine Spearman: 86.25
+- Manhattan Pearson: 84.80
+- Manhattan Spearman: 85.27
+- Euclidean Pearson: 84.79
+- Euclidean Spearman: 85.25
+- Dot Pearson: 82.93
+- Dot Spearman: 82.86
+
+## Training
+
+The model was trained with the parameters:
+
+**DataLoader**:
+
+`sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader` of length 4442 with parameters:
+
+```
+{'batch_size': 128}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
+
+  ```
+  {'scale': 20.0, 'similarity_fct': 'cos_sim'}
+  ```
+
+**DataLoader**:
+
+`torch.utils.data.dataloader.DataLoader` of length 719 with parameters:
+
+```
+{'batch_size': 8, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss`
+
+Parameters of the fit()-Method:
+
+```
+{
+    "epochs": 10,
+    "evaluation_steps": 1000,
+    "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": 719,
+    "weight_decay": 0.01
+}
+```
+
+## Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: DebertaV2Model 
+  (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, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->
+
+```bibtex
+@proceedings{jeon-etal-2023-kfdeberta,
+  title         = {KF-DeBERTa: Financial Domain-specific Pre-trained Language Model},
+  author        = {Eunkwang Jeon, Jungdae Kim, Minsang Song, and Joohyun Ryu},
+  booktitle     = {Proceedings of the 35th Annual Conference on Human and Cognitive Language Technology},
+  moth          = {oct},
+  year          = {2023},
+  publisher     = {Korean Institute of Information Scientists and Engineers},
+  url           = {http://www.hclt.kr/symp/?lnb=conference},
+  pages         = {143--148},
+}
+```
+
+```bibtex
+@article{ham2020kornli,
+  title={KorNLI and KorSTS: New Benchmark Datasets for Korean Natural Language Understanding},
+  author={Ham, Jiyeon and Choe, Yo Joong and Park, Kyubyong and Choi, Ilji and Soh, Hyungjoon},
+  journal={arXiv preprint arXiv:2004.03289},
+  year={2020}
+}
+```

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "kakaobank/kf-deberta-base",
+  "architectures": [
+    "DebertaV2Model"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "conv_act": "gelu",
+  "conv_kernel_size": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.1",
+  "type_vocab_size": 0,
+  "vocab_size": 130000
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.36.1",
+    "pytorch": "1.11.0"
+  }
+}

eval/similarity_evaluation_sts-dev_results.csv

@@ -0,0 +1,11 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,-1,0.8662204956565079,0.8701433627944452,0.8565443779563348,0.8613773571708476,0.8560883635989125,0.8606584545362987,0.8202927967048539,0.8194888085039882
+1,-1,0.8739205955213473,0.8758925251709859,0.8653773959530131,0.8692820156859796,0.8647304570456534,0.8685202340180903,0.8314283990734999,0.8297083397755294
+2,-1,0.873226762046955,0.8742324546170553,0.861951917180206,0.8673471958368025,0.8610252712798507,0.8664120314862117,0.8305024207148536,0.8302137280264562
+3,-1,0.8748335444633338,0.8761404940944174,0.8666428028248511,0.8715341827306609,0.8659880687821292,0.8707590362848057,0.8329152465384382,0.8299645392415027
+4,-1,0.8751374826185992,0.875617777648221,0.8628455122246389,0.8685438059808782,0.8621695407968285,0.867591484262702,0.8386198188718612,0.8382529150976307
+5,-1,0.8757745589038899,0.8748982130889459,0.863903994123835,0.8692367380744607,0.8636271881511799,0.8688871933476968,0.8378372858859178,0.8365435829510706
+6,-1,0.8749608603797978,0.875302211591622,0.8651230938909044,0.870590183854361,0.8644454465711514,0.8697119537070153,0.8394965792357566,0.8371347185924382
+7,-1,0.8756642281042165,0.8754720764788898,0.8655350874061635,0.8707828014258668,0.8648885722256727,0.8700175677982847,0.8387960733830822,0.8356778955178322
+8,-1,0.8764719870550455,0.8762953653098642,0.8664626408021754,0.8717207397997367,0.865835356014391,0.8710521094420978,0.8403957938235846,0.8376097829789138
+9,-1,0.8761662638270564,0.8756781922811445,0.8662225168104593,0.8713532075159957,0.865570210666156,0.8706111322674874,0.8409601713130908,0.8385279740072908

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acb29ec9aa58f05568fa6e42b8621fa701fc8fd1873f1a4a5f9122b907596c66
+size 741185640

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 sha256:3390b04cd5ca99e759732e19660344e27e5107a09c755bfb6cf7a6e48afc92bd
+size 741238901

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "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,-1,0.8574826210027622,0.8625167208630782,0.8478939146405619,0.8524540783146085,0.8480117776348778,0.8527497844953591,0.8293372739387574,0.8286020232145503

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "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 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "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]"
+}