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": 384,
+  "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 384 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 73 with parameters:
+```
+{'batch_size': 8, '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": 29,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, '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 +1,26 @@
+{
+  "_name_or_path": "intfloat/multilingual-e5-small",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

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
+0,50,0.5567010309278351,0.7542955326460481,0.8264604810996563,0.8694158075601375,0.5567010309278351,0.5567010309278351,0.25143184421534936,0.7542955326460481,0.16529209621993124,0.8264604810996563,0.08694158075601374,0.8694158075601375,0.6698099056346475,0.718825314652274,0.6744847494298459,0.5567010309278351,0.7542955326460481,0.8264604810996563,0.8694158075601375,0.5567010309278351,0.5567010309278351,0.25143184421534936,0.7542955326460481,0.16529209621993124,0.8264604810996563,0.08694158075601374,0.8694158075601375,0.6698099056346475,0.718825314652274,0.6744847494298459
+0,-1,0.6082474226804123,0.7955326460481099,0.8298969072164949,0.8831615120274914,0.6082474226804123,0.6082474226804123,0.26517754868270327,0.7955326460481099,0.16597938144329896,0.8298969072164949,0.08831615120274913,0.8831615120274914,0.7074626356842848,0.7504960476095114,0.7120835805867819,0.6082474226804123,0.7955326460481099,0.8298969072164949,0.8831615120274914,0.6082474226804123,0.6082474226804123,0.26517754868270327,0.7955326460481099,0.16597938144329896,0.8298969072164949,0.08831615120274913,0.8831615120274914,0.7074626356842848,0.7504960476095114,0.7120835805867819
+1,50,0.654639175257732,0.8195876288659794,0.8573883161512027,0.9072164948453608,0.654639175257732,0.654639175257732,0.27319587628865977,0.8195876288659794,0.17147766323024052,0.8573883161512027,0.09072164948453607,0.9072164948453608,0.7463487972508587,0.7857213442855117,0.7497176044764986,0.654639175257732,0.8195876288659794,0.8573883161512027,0.9072164948453608,0.654639175257732,0.654639175257732,0.27319587628865977,0.8195876288659794,0.17147766323024052,0.8573883161512027,0.09072164948453607,0.9072164948453608,0.7463487972508587,0.7857213442855117,0.7497176044764986
+1,-1,0.6580756013745704,0.8298969072164949,0.8625429553264605,0.9089347079037801,0.6580756013745704,0.6580756013745704,0.2766323024054983,0.8298969072164949,0.1725085910652921,0.8625429553264605,0.09089347079037799,0.9089347079037801,0.750901380025091,0.789721934542955,0.7542484517919128,0.6580756013745704,0.8298969072164949,0.8625429553264605,0.9089347079037801,0.6580756013745704,0.6580756013745704,0.2766323024054983,0.8298969072164949,0.1725085910652921,0.8625429553264605,0.09089347079037799,0.9089347079037801,0.750901380025091,0.789721934542955,0.7542484517919128
+2,50,0.6804123711340206,0.8333333333333334,0.8711340206185567,0.9140893470790378,0.6804123711340206,0.6804123711340206,0.27777777777777773,0.8333333333333334,0.1742268041237113,0.8711340206185567,0.09140893470790376,0.9140893470790378,0.7654434626084108,0.8018113009539394,0.7685901193579829,0.6804123711340206,0.8333333333333334,0.8711340206185567,0.9140893470790378,0.6804123711340206,0.6804123711340206,0.27777777777777773,0.8333333333333334,0.1742268041237113,0.8711340206185567,0.09140893470790376,0.9140893470790378,0.7654434626084108,0.8018113009539394,0.7685901193579829
+2,-1,0.6804123711340206,0.8367697594501718,0.8711340206185567,0.9123711340206185,0.6804123711340206,0.6804123711340206,0.2789232531500572,0.8367697594501718,0.1742268041237113,0.8711340206185567,0.09123711340206185,0.9123711340206185,0.7664839360715645,0.8023234830993669,0.7697478599339987,0.6804123711340206,0.8367697594501718,0.8711340206185567,0.9123711340206185,0.6804123711340206,0.6804123711340206,0.2789232531500572,0.8367697594501718,0.1742268041237113,0.8711340206185567,0.09123711340206185,0.9123711340206185,0.7664839360715645,0.8023234830993669,0.7697478599339987
+3,50,0.6907216494845361,0.8384879725085911,0.8711340206185567,0.9123711340206185,0.6907216494845361,0.6907216494845361,0.279495990836197,0.8384879725085911,0.17422680412371133,0.8711340206185567,0.09123711340206185,0.9123711340206185,0.7725004090983472,0.8068171099919846,0.7757696385305275,0.6907216494845361,0.8384879725085911,0.8711340206185567,0.9123711340206185,0.6907216494845361,0.6907216494845361,0.279495990836197,0.8384879725085911,0.17422680412371133,0.8711340206185567,0.09123711340206185,0.9123711340206185,0.7725004090983472,0.8068171099919846,0.7757696385305275
+3,-1,0.6924398625429553,0.8419243986254296,0.8711340206185567,0.9123711340206185,0.6924398625429553,0.6924398625429553,0.28064146620847646,0.8419243986254296,0.17422680412371133,0.8711340206185567,0.09123711340206185,0.9123711340206185,0.7738777068673973,0.8078589373909261,0.7771469697426756,0.6924398625429553,0.8419243986254296,0.8711340206185567,0.9123711340206185,0.6924398625429553,0.6924398625429553,0.28064146620847646,0.8419243986254296,0.17422680412371133,0.8711340206185567,0.09123711340206185,0.9123711340206185,0.7738777068673973,0.8078589373909261,0.7771469697426756

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaec225a8f075461b6b9c775f7e9e72b717b2ae1048708640098aeea96ee9b9c
+size 470637416

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": false,
+    "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 sha256:45b6ee00bc5023ac454b82c372ebe14b27866fa471b6dbb0d24e09b12909a1f4
+size 17083075

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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": false,
+      "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>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}