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": 1024,
+  "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 +1,88 @@
+---
+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 1024 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 899 with parameters:
+```
+{'batch_size': 64, '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": 500,
+    "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": 899,
+    "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': 1024, '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": "/root/.cache/torch/sentence_transformers/intfloat_multilingual-e5-large/",
+  "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": "4.33.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.33.2",
+    "pytorch": "2.0.1+cu118"
+  }
+}

eval/similarity_evaluation_sts-dev_results.csv

@@ -0,0 +1,21 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,500,0.8883798973219105,0.887870787495745,0.8790538896743093,0.8878706853039802,0.8791091868607182,0.8876980927583397,0.8883798986523815,0.8878707986822441
+0,-1,0.8839876247184333,0.8847917493162002,0.8745458183922462,0.8847916824835239,0.8746944956700128,0.8846482264217472,0.8839876257542536,0.8847917628759879
+1,500,0.8873975242564914,0.8866828709033358,0.8753503864315072,0.886682802013127,0.8752510550289968,0.8863009559697205,0.8873975245833597,0.8866827824233574
+1,-1,0.8895262945032003,0.8897451889997742,0.8754940839945776,0.8897450535542353,0.8754669729660346,0.8894300792421012,0.8895262938105865,0.889745097307778
+2,500,0.8875013083724845,0.8877101534876415,0.8750210524171467,0.8877100493005433,0.8749661110917248,0.8873933370043758,0.8875013084437873,0.8877100127634171
+2,-1,0.8864915117265574,0.886293239940057,0.8734786329950134,0.8862932162175419,0.8733708791086711,0.8859235283766459,0.886491511589725,0.8862931709695155
+3,500,0.887381587658178,0.8876305236619703,0.8746039999984911,0.8876304033206879,0.8746417473483139,0.8873213232630155,0.8873815887195815,0.8876305324368694
+3,-1,0.8867399624113336,0.8873752186453284,0.8742297234802799,0.8873753695743908,0.8742697758235519,0.8871495319405628,0.8867399619480085,0.8873754865711466
+4,500,0.8880466858407022,0.8883635164208331,0.8740469804997246,0.8883635049430316,0.8740821206008674,0.8881260427847135,0.8880466863877221,0.8883636582837685
+4,-1,0.8849564522516911,0.8866185068964364,0.8726707025699778,0.8866184666227281,0.8727297157798393,0.8864609286893641,0.8849564517298162,0.8866188024207167
+5,500,0.8850553679692099,0.8861017306557776,0.8713011402812649,0.8861017668211482,0.8712380724471809,0.8858009490548743,0.8850553664604457,0.8861020283947733
+5,-1,0.8880684526486442,0.8886220311034116,0.8733475857327055,0.8886219806478253,0.8733596430854653,0.8883842527001425,0.8880684527314678,0.8886220289061718
+6,500,0.8872486638104244,0.8879720013700346,0.8726343226277433,0.8879719157659529,0.8726502770809318,0.887749996918837,0.8872486626325269,0.8879720607437894
+6,-1,0.8871584048967072,0.8877010099412453,0.8724368235820202,0.8877009704358382,0.8724207429373498,0.8874779052528715,0.8871584025523012,0.8877009293559392
+7,500,0.8868892707317143,0.8877620733580288,0.8720646141503575,0.8877620016819212,0.87210069914294,0.8875900605321617,0.8868892673858905,0.887761960038787
+7,-1,0.8873177862938347,0.8879268808406039,0.8725229505072006,0.8879267876161419,0.8725324032509777,0.8877260002681355,0.887317790439103,0.8879267507417973
+8,500,0.8869819489339983,0.8878879016689981,0.8722494215755754,0.8878877769943294,0.8722476722386895,0.8876951641066864,0.8869819515749983,0.8878876721570182
+8,-1,0.88678327230998,0.8876092070747446,0.8720669857067609,0.8876092650714897,0.8721283256930009,0.8874795913481924,0.8867832712907384,0.8876093337309763
+9,500,0.8868302542467523,0.8874740790913506,0.8718789080208413,0.8874741299711257,0.8719441891131061,0.8873390219321152,0.8868302533592062,0.8874740261435213
+9,-1,0.8867406686402729,0.8873880151311151,0.8716959346068037,0.8873880097946676,0.8717361983823629,0.8872416209120161,0.886740669477697,0.8873879192954958

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 sha256:5747a8ba117739fded8bb1d966ab08ace6b9235c7e0116d03d5b682c6fa45e64
+size 2239693545

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>"
+}