Upload folder using huggingface_hub

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 598 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": 2,
+    "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": 119,
+    "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 +1,25 @@
+{
+  "_name_or_path": "thenlper/gte-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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,9 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.7.0",
+    "transformers": "4.44.0",
+    "pytorch": "2.4.0+cpu"
+  },
+  "prompts": {},
+  "default_prompt_name": null
+}

eval/Information-Retrieval_evaluation_results.csv

@@ -0,0 +1,11 @@
+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
+0,50,0.026258571667502926,0.04649606957685232,0.054524167921057035,0.06472654290015052,0.026258571667502926,0.026258571667502926,0.015498689858950771,0.04649606957685232,0.010904833584211408,0.054524167921057035,0.006472654290015053,0.06472654290015052,0.038833270945664314,0.04504177347982284,0.04061445905884576,0.025422311423314935,0.04716507777220271,0.054356915872219434,0.06539555109550092,0.025422311423314935,0.025422311423314935,0.015721692590734235,0.04716507777220271,0.010871383174443887,0.054356915872219434,0.006539555109550092,0.06539555109550092,0.038541044449223065,0.044976589285204524,0.04025833884955975
+0,100,0.023415286837263755,0.04917210235825389,0.05954172938618498,0.06991135641411607,0.023415286837263755,0.023415286837263755,0.01639070078608463,0.04917210235825389,0.011908345877236999,0.05954172938618498,0.006991135641411607,0.06991135641411607,0.039449979690822624,0.046832433168035224,0.041224340490682784,0.023415286837263755,0.04950660645592909,0.05970898143502258,0.07007860846295368,0.023415286837263755,0.023415286837263755,0.016502202151976363,0.04950660645592909,0.011941796287004517,0.05970898143502258,0.007007860846295368,0.07007860846295368,0.039519668044504956,0.04692765368014872,0.041277933447703696
+0,150,0.030607124937280482,0.05653119250710821,0.0665663154373641,0.07777220270948319,0.030607124937280482,0.030607124937280482,0.018843730835702736,0.05653119250710821,0.013313263087472823,0.0665663154373641,0.007777220270948319,0.07777220270948319,0.046443172797914364,0.05400117698425062,0.048057733438054674,0.030439872888442885,0.055862184311757816,0.0669008195350393,0.0772704465629704,0.030439872888442885,0.030439872888442885,0.01862072810391927,0.055862184311757816,0.013380163907007862,0.0669008195350393,0.00772704465629704,0.0772704465629704,0.046223886778327276,0.05372602247553259,0.04789012055105863
+0,200,0.03294865362100686,0.05954172938618498,0.06957685231644088,0.08262251212577354,0.03294865362100686,0.03294865362100686,0.019847243128728324,0.05954172938618498,0.013915370463288173,0.06957685231644088,0.008262251212577355,0.08262251212577354,0.04941627707558461,0.05741182025058456,0.051464800989675014,0.03328315771868205,0.05903997323967219,0.06957685231644088,0.08161899983274795,0.03328315771868205,0.03328315771868205,0.019679991079890727,0.05903997323967219,0.013915370463288175,0.06957685231644088,0.008161899983274795,0.08161899983274795,0.04936238474873694,0.05714255263085033,0.05143440926933393
+0,250,0.03311590566984446,0.06322127446061214,0.07409265763505603,0.08730556949322629,0.03311590566984446,0.03311590566984446,0.021073758153537382,0.06322127446061214,0.014818531527011207,0.07409265763505603,0.00873055694932263,0.08730556949322629,0.05125790796889641,0.05995033634611925,0.05321594692577556,0.032446897474494064,0.06271951831409935,0.07359090148854323,0.0868038133467135,0.032446897474494064,0.032446897474494064,0.020906506104699782,0.06271951831409935,0.014718180297708647,0.07359090148854323,0.008680381334671349,0.0868038133467135,0.05071944928944426,0.059422906307333476,0.052701401496641515
+0,300,0.032446897474494064,0.06071249372804817,0.07409265763505603,0.08830908178625188,0.032446897474494064,0.032446897474494064,0.02023749790934939,0.06071249372804817,0.014818531527011205,0.07409265763505603,0.008830908178625188,0.08830908178625188,0.050333043960740856,0.05943994312733791,0.05248285950342618,0.032446897474494064,0.06087974577688577,0.07492891787924402,0.08897808998160227,0.032446897474494064,0.032446897474494064,0.02029324859229525,0.06087974577688577,0.014985783575848805,0.07492891787924402,0.008897808998160228,0.08897808998160227,0.0505617545005402,0.05977467899249539,0.05269944941777284
+0,350,0.035290182304733235,0.06539555109550092,0.07559792607459441,0.08981435022579026,0.035290182304733235,0.035290182304733235,0.021798517031833636,0.06539555109550092,0.015119585214918884,0.07559792607459441,0.008981435022579027,0.08981435022579026,0.05324409241870357,0.06205666467473974,0.05552659704776595,0.03562468640240843,0.06539555109550092,0.07576517812343202,0.08947984612811508,0.03562468640240843,0.03562468640240843,0.021798517031833636,0.06539555109550092,0.015153035624686402,0.07576517812343202,0.008947984612811507,0.08947984612811508,0.053400393440533954,0.062098309381166485,0.055688620134265565
+0,400,0.03361766181635725,0.06205051011874895,0.07208563304900485,0.0859675531025255,0.03361766181635725,0.03361766181635725,0.02068350337291632,0.06205051011874895,0.01441712660980097,0.07208563304900485,0.008596755310252552,0.0859675531025255,0.05070365326260956,0.05917645439057062,0.05293814124024115,0.03328315771868205,0.06171600602107376,0.07175112895132965,0.08513129285833751,0.03328315771868205,0.03328315771868205,0.020572002007024585,0.06171600602107376,0.014350225790265932,0.07175112895132965,0.008513129285833752,0.08513129285833751,0.05028857615410546,0.05867093518545372,0.052545026906250215
+0,450,0.03361766181635725,0.05970898143502258,0.07091486870714166,0.08262251212577354,0.03361766181635725,0.03361766181635725,0.01990299381167419,0.05970898143502258,0.014182973741428335,0.07091486870714166,0.008262251212577355,0.08262251212577354,0.049422051253461156,0.05741031174309137,0.051788300042591225,0.03278140157216926,0.059876233483860175,0.07074761665830406,0.08212075597926075,0.03278140157216926,0.03278140157216926,0.019958744494620057,0.059876233483860175,0.014149523331660814,0.07074761665830406,0.008212075597926076,0.08212075597926075,0.048954276475601084,0.0569481303112754,0.05133169008966853
+0,500,0.035290182304733235,0.06506104699782572,0.07559792607459441,0.08914534203043988,0.035290182304733235,0.035290182304733235,0.021687015665941903,0.06506104699782572,0.015119585214918884,0.07559792607459441,0.008914534203043988,0.08914534203043988,0.053178452626520815,0.06183823905923685,0.05558342414857123,0.035122930255895635,0.06539555109550092,0.07559792607459441,0.08931259407927747,0.035122930255895635,0.035122930255895635,0.021798517031833636,0.06539555109550092,0.015119585214918884,0.07559792607459441,0.008931259407927748,0.08931259407927747,0.05316610783243995,0.06187401027221343,0.05555400047140864

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6664823b17ffc9899cfba4ebb222658b19083fc097672caa58655112cb66313e
+size 133462128

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
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "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 +1,64 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}