Upload folder using huggingface_hub

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

@@ -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 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 1432 with parameters:
+```
+{'batch_size': 10, '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": 1,
+    "evaluation_steps": 200,
+    "evaluator": "sentence_transformers.evaluation.BinaryClassificationEvaluator.BinaryClassificationEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
+    "optimizer_params": {
+        "lr": 0.0001
+    },
+    "scheduler": "warmuplinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 143,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: MPNetModel 
+  (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 +1,24 @@
+{
+  "_name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_multi-qa-mpnet-base-cos-v1/",
+  "architectures": [
+    "MPNetModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "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": "mpnet",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "vocab_size": 30527
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.0.0",
+    "transformers": "4.6.1",
+    "pytorch": "1.8.1"
+  }
+}

eval/binary_classification_evaluation_results_results.csv

@@ -0,0 +1,9 @@
+epoch,steps,cossim_accuracy,cossim_accuracy_threshold,cossim_f1,cossim_precision,cossim_recall,cossim_f1_threshold,cossim_ap,manhattan_accuracy,manhattan_accuracy_threshold,manhattan_f1,manhattan_precision,manhattan_recall,manhattan_f1_threshold,manhattan_ap,euclidean_accuracy,euclidean_accuracy_threshold,euclidean_f1,euclidean_precision,euclidean_recall,euclidean_f1_threshold,euclidean_ap,dot_accuracy,dot_accuracy_threshold,dot_f1,dot_precision,dot_recall,dot_f1_threshold,dot_ap
+0,200,0.7844441427989683,0.49500977993011475,0.5901417960837272,0.5559796437659033,0.6287769784172662,0.3809729516506195,0.6535653579973784,0.7848513641916656,21.50560760498047,0.5919670442842431,0.5187725631768954,0.6892086330935252,24.42305564880371,0.6540328132343743,0.7844441427989683,1.0049777030944824,0.5901417960837272,0.5559796437659033,0.6287769784172662,1.1126787662506104,0.6535653579973784,0.7844441427989683,0.4950098693370819,0.5901417960837272,0.5559796437659033,0.6287769784172662,0.3809729218482971,0.6535653031626607
+0,400,0.7172526130039365,1.0,0.4412231509893133,0.28305729025251153,1.0,0.9999727010726929,0.2783653417357731,0.7171168725397041,0.0031983614899218082,0.4412231509893133,0.28305729025251153,1.0,0.16016513109207153,0.27871519887446783,0.7171168725397041,0.00014417964848689735,0.4412231509893133,0.28305729025251153,1.0,0.007390656042844057,0.2787511121244277,0.7169811320754716,1.0,0.4412231509893133,0.28305729025251153,1.0,0.9999727010726929,0.2780625388018211
+0,600,0.7171168725397041,1.0,0.44131654143295584,0.2831341662140141,1.0,0.9999960660934448,0.2810871690272637,0.7169811320754716,0.0008220643503591418,0.44131654143295584,0.2831341662140141,1.0,0.05916962772607803,0.2834598548798023,0.7169811320754716,3.750418545678258e-05,0.44131654143295584,0.2831341662140141,1.0,0.002790421014651656,0.2833997018292086,0.7168453916112393,1.0000001192092896,0.44131654143295584,0.2831341662140141,1.0,0.9999961256980896,0.28430597296468607
+0,800,0.7171168725397041,1.0,0.44131654143295584,0.2831341662140141,1.0,0.9999932646751404,0.28445430876533107,0.7168453916112393,0.000544880866073072,0.4412698412698413,0.2830957230142566,1.0,0.08449363708496094,0.28436796168639017,0.7168453916112393,2.5259887479478493e-05,0.4412698412698413,0.2830957230142566,1.0,0.003975867293775082,0.28439490106410464,0.7168453916112393,1.0000001192092896,0.44131654143295584,0.2831341662140141,1.0,0.9999933242797852,0.2841713193742575
+0,1000,0.7171168725397041,1.0,0.4419197281800807,0.2837856266193918,0.9980815347721822,0.9999997615814209,0.2858759033673937,0.7168453916112393,0.0005671593244187534,0.44166047351098847,0.28361058085628577,0.9976019184652278,0.015263278968632221,0.28422959601321585,0.7168453916112393,2.5454743081354536e-05,0.44170736886812484,0.2836492567843993,0.9976019184652278,0.0006895815022289753,0.28441911678979653,0.7168453916112393,1.000000238418579,0.4416303075449612,0.2837800875273523,0.9952038369304557,0.9999997615814209,0.285439578702063
+0,1200,0.7171168725397041,1.0,0.44142902576062754,0.2833424060968971,0.9985611510791367,0.9999998211860657,0.28355915210198385,0.7168453916112393,0.0005712748970836401,0.44142902576062754,0.2833424060968971,0.9985611510791367,0.013972094282507896,0.28517121461111716,0.7168453916112393,2.564379246905446e-05,0.4415694591728526,0.2834581347855684,0.9985611510791367,0.0006229695864021778,0.285367014649916,0.7172526130039365,1.0000001192092896,0.44189261031366295,0.28387978142076503,0.996642685851319,0.9999997615814209,0.2784220621627503
+0,1400,0.7171168725397041,1.0,0.44166047351098847,0.28361058085628577,0.9976019184652278,0.9999998807907104,0.2850134610919487,0.7168453916112393,0.0006067490903660655,0.4427251235761874,0.28527904722337627,0.988009592326139,0.009999344125390053,0.2855478122259374,0.7168453916112393,2.7855783628183417e-05,0.443010752688172,0.2855162855162855,0.988009592326139,0.0004502631491050124,0.28572036692417946,0.7172526130039365,1.0000001192092896,0.44152263810836606,0.2834195480533624,0.9985611510791367,0.9999997615814209,0.28335390703610996
+0,-1,0.7171168725397041,1.0,0.44170736886812484,0.2836492567843993,0.9976019184652278,0.9999998807907104,0.2848590218776231,0.7168453916112393,0.0006069369846954942,0.4428694158075602,0.28531894285318943,0.988968824940048,0.010157727636396885,0.28558635178523945,0.7168453916112393,2.786061668302864e-05,0.44274973147153607,0.28525951557093426,0.9884892086330935,0.00045753229642286897,0.2857500239674161,0.7171168725397041,1.0000001192092896,0.44152263810836606,0.2834195480533624,0.9985611510791367,0.9999997615814209,0.284376251565123

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7f914c5cd6f29b3f4749f8e7b7b729867bd992f6b1ff75d0fee4b3d19a20d94
+size 437967672

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 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "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": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,72 @@
+{
+  "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": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30526": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 250,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MPNetTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}