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 +1,7 @@
+{
+  "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

@@ -1,5 +1,91 @@
 ---
-license: other
-license_name: hunet
-license_link: LICENSE
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+
 ---
+
+# {MODEL_NAME}
+
+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.
+
+<!--- 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 = ["This is an example sentence", "Each sentence is converted"]
+
+model = SentenceTransformer('{MODEL_NAME}')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+
+
+## Evaluation Results
+
+<!--- Describe how your model was evaluated -->
+
+For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
+
+
+## Training
+The model was trained with the parameters:
+
+**DataLoader**:
+
+`torch.utils.data.dataloader.DataLoader` of length 52 with parameters:
+```
+{'batch_size': 32, 'sampler': 'torch.utils.data.sampler.SequentialSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
+  ```
+  {'scale': 20.0, 'similarity_fct': 'cos_sim'}
+  ```
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 10,
+    "evaluation_steps": 50,
+    "evaluator": "sentence_transformers.evaluation.InformationRetrievalEvaluator.InformationRetrievalEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
+    "optimizer_params": {
+        "lr": 2e-05
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 52,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (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})
+  (2): Normalize()
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/nas_data/nlu_resources/default/ko/models/sentence-transformers/multilingual-e5-base/",
+  "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": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config.pbtxt

@@ -0,0 +1,22 @@
+name: "sentence_1"
+platform: "pytorch_libtorch"
+max_batch_size: 128
+input [
+  {
+    name: "INPUT__0"
+    data_type: TYPE_FP32
+    dims: [ -1 ]
+  },
+  {
+    name: "INPUT__1"
+    data_type: TYPE_FP32
+    dims: [ -1 ]
+  }
+]
+output [
+  {
+    name: "OUTPUT__0"
+    data_type: TYPE_FP32
+    dims: [ 384 ]
+  }
+]

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.33.1",
+    "pytorch": "2.0.1+cu117"
+  }
+}

eval/Information-Retrieval_evaluation_results.csv

@@ -0,0 +1,21 @@
+epoch,steps,cos_sim-Accuracy@1,cos_sim-Accuracy@3,cos_sim-Accuracy@5,cos_sim-Accuracy@10,cos_sim-Precision@1,cos_sim-Recall@1,cos_sim-Precision@3,cos_sim-Recall@3,cos_sim-Precision@5,cos_sim-Recall@5,cos_sim-Precision@10,cos_sim-Recall@10,cos_sim-MRR@10,cos_sim-NDCG@10,cos_sim-MAP@100,dot_score-Accuracy@1,dot_score-Accuracy@3,dot_score-Accuracy@5,dot_score-Accuracy@10,dot_score-Precision@1,dot_score-Recall@1,dot_score-Precision@3,dot_score-Recall@3,dot_score-Precision@5,dot_score-Recall@5,dot_score-Precision@10,dot_score-Recall@10,dot_score-MRR@10,dot_score-NDCG@10,dot_score-MAP@100
+0,50,0.6646525679758308,0.8181268882175227,0.8670694864048338,0.9293051359516616,0.6646525679758308,0.6646525679758308,0.2727089627391742,0.8181268882175227,0.17341389728096676,0.8670694864048338,0.09293051359516617,0.9293051359516616,0.7533961540305951,0.7959404018070927,0.7566540132264188,0.6646525679758308,0.8181268882175227,0.8670694864048338,0.9293051359516616,0.6646525679758308,0.6646525679758308,0.2727089627391742,0.8181268882175227,0.17341389728096676,0.8670694864048338,0.09293051359516617,0.9293051359516616,0.7533961540305951,0.7959404018070927,0.7566540132264188
+0,-1,0.6809667673716012,0.83202416918429,0.8845921450151057,0.9401812688821752,0.6809667673716012,0.6809667673716012,0.2773413897280967,0.83202416918429,0.17691842900302113,0.8845921450151057,0.09401812688821751,0.9401812688821752,0.7675228983839253,0.8093613476956427,0.7702380235248609,0.6809667673716012,0.83202416918429,0.8845921450151057,0.9401812688821752,0.6809667673716012,0.6809667673716012,0.2773413897280967,0.83202416918429,0.17691842900302113,0.8845921450151057,0.09401812688821751,0.9401812688821752,0.7675228983839253,0.8093613476956427,0.7702380235248609
+1,50,0.7528700906344411,0.9063444108761329,0.9438066465256798,0.9776435045317221,0.7528700906344411,0.7528700906344411,0.3021148036253776,0.9063444108761329,0.18876132930513595,0.9438066465256798,0.09776435045317221,0.9776435045317221,0.8352227497242597,0.8702463776669295,0.8364358023079388,0.7528700906344411,0.9063444108761329,0.9438066465256798,0.9776435045317221,0.7528700906344411,0.7528700906344411,0.3021148036253776,0.9063444108761329,0.18876132930513595,0.9438066465256798,0.09776435045317221,0.9776435045317221,0.8352227497242597,0.8702463776669295,0.8364358023079388
+1,-1,0.7552870090634441,0.9093655589123867,0.9444108761329305,0.9794561933534743,0.7552870090634441,0.7552870090634441,0.3031218529707955,0.9093655589123867,0.18888217522658607,0.9444108761329305,0.09794561933534743,0.9794561933534743,0.837529372272574,0.8724547847626435,0.838638411014943,0.7552870090634441,0.9093655589123867,0.9444108761329305,0.9794561933534743,0.7552870090634441,0.7552870090634441,0.3031218529707955,0.9093655589123867,0.18888217522658607,0.9444108761329305,0.09794561933534743,0.9794561933534743,0.837529372272574,0.8724547847626435,0.838638411014943
+2,50,0.7933534743202417,0.9274924471299094,0.9607250755287009,0.9903323262839879,0.7933534743202417,0.7933534743202417,0.3091641490433032,0.9274924471299094,0.19214501510574017,0.9607250755287009,0.09903323262839879,0.9903323262839879,0.8675260154414228,0.8978246893546952,0.8680995621401357,0.7933534743202417,0.9274924471299094,0.9607250755287009,0.9903323262839879,0.7933534743202417,0.7933534743202417,0.3091641490433032,0.9274924471299094,0.19214501510574017,0.9607250755287009,0.09903323262839879,0.9903323262839879,0.8675260154414228,0.8978246893546952,0.8680995621401357
+2,-1,0.7921450151057402,0.9287009063444108,0.9619335347432024,0.9915407854984895,0.7921450151057402,0.7921450151057402,0.30956696878147033,0.9287009063444108,0.19238670694864046,0.9619335347432024,0.09915407854984895,0.9915407854984895,0.8671785834172537,0.8978469527041625,0.8676471409985838,0.7921450151057402,0.9287009063444108,0.9619335347432024,0.9915407854984895,0.7921450151057402,0.7921450151057402,0.30956696878147033,0.9287009063444108,0.19238670694864046,0.9619335347432024,0.09915407854984895,0.9915407854984895,0.8671785834172537,0.8978469527041625,0.8676471409985838
+3,50,0.8108761329305136,0.9462235649546827,0.970392749244713,0.992749244712991,0.8108761329305136,0.8108761329305136,0.31540785498489426,0.9462235649546827,0.1940785498489426,0.970392749244713,0.0992749244712991,0.992749244712991,0.8815081762815896,0.9091512114085066,0.8819351403438042,0.8108761329305136,0.9462235649546827,0.970392749244713,0.992749244712991,0.8108761329305136,0.8108761329305136,0.31540785498489426,0.9462235649546827,0.1940785498489426,0.970392749244713,0.0992749244712991,0.992749244712991,0.8815081762815896,0.9091512114085066,0.8819351403438042
+3,-1,0.8096676737160121,0.9480362537764351,0.9716012084592145,0.992749244712991,0.8096676737160121,0.8096676737160121,0.316012084592145,0.9480362537764351,0.19432024169184292,0.9716012084592145,0.0992749244712991,0.992749244712991,0.8810972042391976,0.9088887922220081,0.8815445798610191,0.8096676737160121,0.9480362537764351,0.9716012084592145,0.992749244712991,0.8096676737160121,0.8096676737160121,0.316012084592145,0.9480362537764351,0.19432024169184292,0.9716012084592145,0.0992749244712991,0.992749244712991,0.8810972042391976,0.9088887922220081,0.8815445798610191
+4,50,0.8283987915407856,0.9528700906344411,0.980060422960725,0.9963746223564954,0.8283987915407856,0.8283987915407856,0.3176233635448137,0.9528700906344411,0.196012084592145,0.980060422960725,0.09963746223564954,0.9963746223564954,0.8931223325181022,0.9187814284341435,0.8933431967495411,0.8283987915407856,0.9528700906344411,0.980060422960725,0.9963746223564954,0.8283987915407856,0.8283987915407856,0.3176233635448137,0.9528700906344411,0.196012084592145,0.980060422960725,0.09963746223564954,0.9963746223564954,0.8931223325181022,0.9187814284341435,0.8933431967495411
+4,-1,0.8290030211480363,0.9534743202416919,0.9794561933534743,0.9957703927492447,0.8290030211480363,0.8290030211480363,0.31782477341389725,0.9534743202416919,0.19589123867069488,0.9794561933534743,0.09957703927492446,0.9957703927492447,0.8932884956600963,0.9187721668316193,0.8935672917651111,0.8290030211480363,0.9534743202416919,0.9794561933534743,0.9957703927492447,0.8290030211480363,0.8290030211480363,0.31782477341389725,0.9534743202416919,0.19589123867069488,0.9794561933534743,0.09957703927492446,0.9957703927492447,0.8932884956600963,0.9187721668316193,0.8935672917651111
+5,50,0.8308157099697885,0.9534743202416919,0.9782477341389728,0.9969788519637462,0.8308157099697885,0.8308157099697885,0.31782477341389725,0.9534743202416919,0.19564954682779453,0.9782477341389728,0.09969788519637462,0.9969788519637462,0.8957317891910036,0.9209172780706709,0.8959318168354956,0.8308157099697885,0.9534743202416919,0.9782477341389728,0.9969788519637462,0.8308157099697885,0.8308157099697885,0.31782477341389725,0.9534743202416919,0.19564954682779453,0.9782477341389728,0.09969788519637462,0.9969788519637462,0.8957317891910036,0.9209172780706709,0.8959318168354956
+5,-1,0.8314199395770393,0.9528700906344411,0.9788519637462235,0.9969788519637462,0.8314199395770393,0.8314199395770393,0.3176233635448137,0.9528700906344411,0.1957703927492447,0.9788519637462235,0.09969788519637462,0.9969788519637462,0.8959523809523806,0.921069380578628,0.8961524085968728,0.8314199395770393,0.9528700906344411,0.9788519637462235,0.9969788519637462,0.8314199395770393,0.8314199395770393,0.3176233635448137,0.9528700906344411,0.1957703927492447,0.9788519637462235,0.09969788519637462,0.9969788519637462,0.8959523809523806,0.921069380578628,0.8961524085968728
+6,50,0.8332326283987915,0.9577039274924471,0.980060422960725,0.9969788519637462,0.8332326283987915,0.8332326283987915,0.31923464249748235,0.9577039274924471,0.19601208459214503,0.980060422960725,0.09969788519637462,0.9969788519637462,0.897780175514314,0.9225102967056847,0.8979914943181337,0.8332326283987915,0.9577039274924471,0.980060422960725,0.9969788519637462,0.8332326283987915,0.8332326283987915,0.31923464249748235,0.9577039274924471,0.19601208459214503,0.980060422960725,0.09969788519637462,0.9969788519637462,0.897780175514314,0.9225102967056847,0.8979914943181337
+6,-1,0.83202416918429,0.9577039274924471,0.980060422960725,0.9969788519637462,0.83202416918429,0.83202416918429,0.31923464249748235,0.9577039274924471,0.19601208459214503,0.980060422960725,0.09969788519637462,0.9969788519637462,0.8971567640147694,0.922044771732557,0.8973680828185893,0.83202416918429,0.9577039274924471,0.980060422960725,0.9969788519637462,0.83202416918429,0.83202416918429,0.31923464249748235,0.9577039274924471,0.19601208459214503,0.980060422960725,0.09969788519637462,0.9969788519637462,0.8971567640147694,0.922044771732557,0.8973680828185893
+7,50,0.8404833836858006,0.9601208459214502,0.9830815709969789,0.997583081570997,0.8404833836858006,0.8404833836858006,0.3200402819738168,0.9601208459214502,0.1966163141993958,0.9830815709969789,0.0997583081570997,0.997583081570997,0.9018704742722866,0.9257071580151973,0.9020326176794988,0.8404833836858006,0.9601208459214502,0.9830815709969789,0.997583081570997,0.8404833836858006,0.8404833836858006,0.3200402819738168,0.9601208459214502,0.1966163141993958,0.9830815709969789,0.0997583081570997,0.997583081570997,0.9018704742722866,0.9257071580151973,0.9020326176794988
+7,-1,0.8398791540785498,0.9601208459214502,0.9830815709969789,0.997583081570997,0.8398791540785498,0.8398791540785498,0.3200402819738168,0.9601208459214502,0.1966163141993958,0.9830815709969789,0.0997583081570997,0.997583081570997,0.9014784443485347,0.925415839862054,0.9016405877557467,0.8398791540785498,0.9601208459214502,0.9830815709969789,0.997583081570997,0.8398791540785498,0.8398791540785498,0.3200402819738168,0.9601208459214502,0.1966163141993958,0.9830815709969789,0.0997583081570997,0.997583081570997,0.9014784443485347,0.925415839862054,0.9016405877557467
+8,50,0.8447129909365559,0.9583081570996979,0.9842900302114803,0.997583081570997,0.8447129909365559,0.8447129909365559,0.3194360523665659,0.9583081570996979,0.19685800604229609,0.9842900302114803,0.0997583081570997,0.997583081570997,0.9045811154270367,0.9277621117982782,0.9047387666043255,0.8447129909365559,0.9583081570996979,0.9842900302114803,0.997583081570997,0.8447129909365559,0.8447129909365559,0.3194360523665659,0.9583081570996979,0.19685800604229609,0.9842900302114803,0.0997583081570997,0.997583081570997,0.9045811154270367,0.9277621117982782,0.9047387666043255
+8,-1,0.8447129909365559,0.9583081570996979,0.9842900302114803,0.997583081570997,0.8447129909365559,0.8447129909365559,0.3194360523665659,0.9583081570996979,0.19685800604229609,0.9842900302114803,0.0997583081570997,0.997583081570997,0.904550903946674,0.9277356321905207,0.9047085551239629,0.8447129909365559,0.9583081570996979,0.9842900302114803,0.997583081570997,0.8447129909365559,0.8447129909365559,0.3194360523665659,0.9583081570996979,0.19685800604229609,0.9842900302114803,0.0997583081570997,0.997583081570997,0.904550903946674,0.9277356321905207,0.9047085551239629
+9,50,0.8459214501510574,0.9583081570996979,0.9842900302114803,0.997583081570997,0.8459214501510574,0.8459214501510574,0.319436052366566,0.9583081570996979,0.19685800604229609,0.9842900302114803,0.0997583081570997,0.997583081570997,0.9054874598379128,0.928445453039107,0.9056422337313577,0.8459214501510574,0.9583081570996979,0.9842900302114803,0.997583081570997,0.8459214501510574,0.8459214501510574,0.319436052366566,0.9583081570996979,0.19685800604229609,0.9842900302114803,0.0997583081570997,0.997583081570997,0.9054874598379128,0.928445453039107,0.9056422337313577
+9,-1,0.8459214501510574,0.9583081570996979,0.9842900302114803,0.997583081570997,0.8459214501510574,0.8459214501510574,0.319436052366566,0.9583081570996979,0.19685800604229609,0.9842900302114803,0.0997583081570997,0.997583081570997,0.9054874598379128,0.928445453039107,0.9056422337313577,0.8459214501510574,0.9583081570996979,0.9842900302114803,0.997583081570997,0.8459214501510574,0.8459214501510574,0.319436052366566,0.9583081570996979,0.19685800604229609,0.9842900302114803,0.0997583081570997,0.997583081570997,0.9054874598379128,0.928445453039107,0.9056422337313577

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90d4dd83444b3475283fbe6b6a40a44d0e5e05715759deadf6ff3c9617bc9079
+size 1112241321

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 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46afe88da5fd71bdbab5cfab5e84c1adce59c246ea5f9341bbecef061891d0a7
+size 17082913

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}