Upload 12 files

.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": 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,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,92 @@
+---
+library_name: sentence-transformers
+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 59 with parameters:
+```
+{'batch_size': 10, '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": 4,
+    "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": 23,
+    "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, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): Normalize()
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "intfloat/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": "4.39.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,9 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.6.1",
+    "transformers": "4.39.3",
+    "pytorch": "2.3.0+cpu"
+  },
+  "prompts": {},
+  "default_prompt_name": null
+}

eval/Information-Retrieval_evaluation_results.csv

@@ -0,0 +1,9 @@
+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
+0,50,0.6391752577319587,0.7989690721649485,0.8470790378006873,0.8900343642611683,0.6391752577319587,0.6391752577319587,0.2663230240549828,0.7989690721649485,0.1694158075601374,0.8470790378006873,0.08900343642611683,0.8900343642611683,0.7308153330060548,0.7698315629602112,0.7349608246472122,0.6391752577319587,0.7989690721649485,0.8470790378006873,0.8900343642611683,0.6391752577319587,0.6391752577319587,0.2663230240549828,0.7989690721649485,0.1694158075601374,0.8470790378006873,0.08900343642611683,0.8900343642611683,0.7308153330060548,0.7698315629602112,0.7349608246472122
+0,-1,0.6649484536082474,0.8127147766323024,0.8608247422680413,0.9020618556701031,0.6649484536082474,0.6649484536082474,0.2709049255441008,0.8127147766323024,0.17216494845360822,0.8608247422680413,0.0902061855670103,0.9020618556701031,0.7477758686521572,0.7853586074809755,0.7514607649671707,0.6649484536082474,0.8127147766323024,0.8608247422680413,0.9020618556701031,0.6649484536082474,0.6649484536082474,0.2709049255441008,0.8127147766323024,0.17216494845360822,0.8608247422680413,0.0902061855670103,0.9020618556701031,0.7477758686521572,0.7853586074809755,0.7514607649671707
+1,50,0.7010309278350515,0.8487972508591065,0.8900343642611683,0.915807560137457,0.7010309278350515,0.7010309278350515,0.2829324169530355,0.8487972508591065,0.17800687285223366,0.8900343642611683,0.0915807560137457,0.915807560137457,0.7825499099983633,0.8154809950834685,0.7855589868510762,0.7010309278350515,0.8487972508591065,0.8900343642611683,0.915807560137457,0.7010309278350515,0.7010309278350515,0.2829324169530355,0.8487972508591065,0.17800687285223366,0.8900343642611683,0.0915807560137457,0.915807560137457,0.7825499099983633,0.8154809950834685,0.7855589868510762
+1,-1,0.7044673539518901,0.8591065292096219,0.8917525773195877,0.915807560137457,0.7044673539518901,0.7044673539518901,0.2863688430698739,0.8591065292096219,0.1783505154639175,0.8917525773195877,0.0915807560137457,0.915807560137457,0.787294087165221,0.8191872218183971,0.7903220393283484,0.7044673539518901,0.8591065292096219,0.8917525773195877,0.915807560137457,0.7044673539518901,0.7044673539518901,0.2863688430698739,0.8591065292096219,0.1783505154639175,0.8917525773195877,0.0915807560137457,0.915807560137457,0.787294087165221,0.8191872218183971,0.7903220393283484
+2,50,0.7164948453608248,0.8694158075601375,0.8986254295532646,0.915807560137457,0.7164948453608248,0.7164948453608248,0.28980526918671246,0.8694158075601375,0.17972508591065292,0.8986254295532646,0.0915807560137457,0.915807560137457,0.7962724322260402,0.826095148308153,0.7995469606673189,0.7164948453608248,0.8694158075601375,0.8986254295532646,0.915807560137457,0.7164948453608248,0.7164948453608248,0.28980526918671246,0.8694158075601375,0.17972508591065292,0.8986254295532646,0.0915807560137457,0.915807560137457,0.7962724322260402,0.826095148308153,0.7995469606673189
+2,-1,0.7199312714776632,0.8711340206185567,0.8951890034364262,0.915807560137457,0.7199312714776632,0.7199312714776632,0.29037800687285226,0.8711340206185567,0.1790378006872852,0.8951890034364262,0.0915807560137457,0.915807560137457,0.7977649593628973,0.8271589378763345,0.8010179808893677,0.7199312714776632,0.8711340206185567,0.8951890034364262,0.915807560137457,0.7199312714776632,0.7199312714776632,0.29037800687285226,0.8711340206185567,0.1790378006872852,0.8951890034364262,0.0915807560137457,0.915807560137457,0.7977649593628973,0.8271589378763345,0.8010179808893677
+3,50,0.7199312714776632,0.8745704467353952,0.8951890034364262,0.9140893470790378,0.7199312714776632,0.7199312714776632,0.2915234822451317,0.8745704467353952,0.1790378006872852,0.8951890034364262,0.09140893470790376,0.9140893470790378,0.7985177003218239,0.8274291887612075,0.8019395117248479,0.7199312714776632,0.8745704467353952,0.8951890034364262,0.9140893470790378,0.7199312714776632,0.7199312714776632,0.2915234822451317,0.8745704467353952,0.1790378006872852,0.8951890034364262,0.09140893470790376,0.9140893470790378,0.7985177003218239,0.8274291887612075,0.8019395117248479
+3,-1,0.7199312714776632,0.8762886597938144,0.8951890034364262,0.9140893470790378,0.7199312714776632,0.7199312714776632,0.2920962199312715,0.8762886597938144,0.1790378006872852,0.8951890034364262,0.09140893470790376,0.9140893470790378,0.7986608847433587,0.8275483012043804,0.8020821698587838,0.7199312714776632,0.8762886597938144,0.8951890034364262,0.9140893470790378,0.7199312714776632,0.7199312714776632,0.2920962199312715,0.8762886597938144,0.1790378006872852,0.8951890034364262,0.09140893470790376,0.9140893470790378,0.7986608847433587,0.8275483012043804,0.8020821698587838

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce26da7fb6b5e469877c098e4c74e1ba4eb551e91d8f36395d6ed39ce27ac5a3
+size 1112197096

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"
+  }
+]

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:f1cc44ad7faaeec47241864835473fd5403f2da94673f3f764a77ebcb0a803ec
+size 17083009

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>"
+}