Upload folder using huggingface_hub

1_Pooling/config.json

@@ -0,0 +1,9 @@
+{
+  "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
+}

README.md

@@ -1,3 +1,89 @@
----
-license: apache-2.0
----
+---
+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 409 with parameters:
+```
+{'batch_size': 32, '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": 5,
+    "evaluation_steps": 100,
+    "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": 100,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 384, '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, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False})
+  (2): Normalize()
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "sentence-transformers/all-mpnet-base-v2",
+  "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": "4.38.1",
+  "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/similarity_evaluation_skill-sim_results.csv

@@ -0,0 +1,27 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,-1,0.9074250703130895,0.8475390598101166,0.883335618952157,0.8475390067626833,0.8828097829881528,0.8474438086435276,0.9074250670682402,0.8475389901853625
+0,100,0.8811465518938596,0.8449982546777575,0.8504639990950765,0.8449982017893531,0.8492675141426367,0.8443285322614986,0.8811465574132885,0.8449982017893531
+0,200,0.893432968813223,0.8454250048937868,0.871232697078271,0.8454249519786722,0.8704632577491047,0.8451689018650806,0.8934329729091016,0.8454249519786722
+0,300,0.9021121926978941,0.8470794826543928,0.876472428222261,0.8470794296357245,0.8759646041281948,0.8470137757604446,0.9021121957876269,0.8470794155526424
+0,400,0.9004716006300841,0.8449522969621851,0.8794785440385481,0.8449522440766571,0.879255178045529,0.8449456786891292,0.9004715998265667,0.8449522440766571
+0,-1,0.8982533082493899,0.8436490682813729,0.8775465966246135,0.8436490146523522,0.8773359817086908,0.84370482044634,0.8982533078600806,0.8436489981511169
+1,100,0.9054214619162557,0.8460355859721057,0.8820106045793857,0.8460355330187749,0.8815985222306473,0.8460617945688867,0.9054214664894469,0.8460355561858557
+1,200,0.9072749657925012,0.8454873760792064,0.8837972758727213,0.8454873231601882,0.8834789973488216,0.8457368078862515,0.9072749655431183,0.8454873057961373
+1,300,0.9073953879033045,0.8449555796561545,0.883718273864631,0.8449555267704212,0.8832673803815466,0.8449817883205332,0.9073953851883625,0.8449555102436315
+1,400,0.91024265807914,0.8465542524471829,0.8871873359372038,0.8465541994613887,0.8867782795383161,0.8465213716958456,0.9102426531370664,0.8465541696568837
+1,-1,0.9113509743129562,0.8467873228911111,0.8873567799110722,0.846787269890729,0.8868762381947779,0.8467248987092132,0.9113509699909941,0.8467872433905418
+2,100,0.9079224361925862,0.844771748793865,0.8831355234884024,0.8447716959196376,0.8826805559752416,0.8448275017136254,0.9079224378198824,0.8447716793964435
+2,200,0.9129400383711164,0.8472797269865296,0.8871189017955359,0.847279673955328,0.886635349180614,0.8473190662804959,0.9129400376553266,0.8472796573830794
+2,300,0.9106874317065572,0.8453724817902756,0.886309807902862,0.8453724288784483,0.8856660832911826,0.8452640999842366,0.9106874314566173,0.8453723999422971
+2,400,0.9123454987243016,0.8455497472646262,0.8876104412554947,0.8455496943417038,0.887077238920549,0.845516867404064,0.9123455001349073,0.8455496728417696
+2,-1,0.9119836114515429,0.8455070722430232,0.8869908624549376,0.8455070193227721,0.8864362232718732,0.8453264711657523,0.9119836097565199,0.845507020149651
+3,100,0.9093288544088511,0.8443482812718052,0.8847464282979657,0.8443482284240826,0.8842695975344278,0.8442989880176226,0.9093288537543877,0.8443482515449598
+3,200,0.9102131030815909,0.8444894371124918,0.8852912384747127,0.8444893842559342,0.8849248175383292,0.8446174101387388,0.9102131016048904,0.8444893842559342
+3,300,0.9091743567270804,0.8438624433895963,0.8841592786539952,0.8438623897470116,0.8836991389361448,0.8437967358717319,0.9091743556688497,0.843862373241603
+3,400,0.9080912022511196,0.8436096751286775,0.8843905662708273,0.8436096223271842,0.8840155451678531,0.8435505338394322,0.9080912046664272,0.8436096231522074
+3,-1,0.9079121884346766,0.8434947808397464,0.8842283192885863,0.8434947288703554,0.8838422782032563,0.8434881626579166,0.9079121891810513,0.8434946999984757
+4,100,0.9088855687098585,0.8433963008454776,0.8847191931273801,0.8433962472325246,0.8842772360859559,0.8434290741701647,0.908885567960144,0.8433962307362334
+4,200,0.9086349842141304,0.8432584268739456,0.8840292636253213,0.843258374094437,0.8835707148726991,0.8432025683004492,0.9086349833321623,0.8432583452306475
+4,300,0.909086540650837,0.843570282801044,0.884754575929251,0.8435702300020163,0.8842959170584099,0.8434980115641226,0.9090865395904701,0.8435702135023221
+4,400,0.9089472683478803,0.8434242037442452,0.8846119743060092,0.8434241509543605,0.8841481698068507,0.8433010491133689,0.9089472692413052,0.8434224922858318
+4,-1,0.908947881034084,0.8434192797032862,0.8846116882660153,0.8434192260888727,0.8841481929694949,0.8433010491133689,0.908947878464997,0.8434192087672951

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daabf35eb1df88fbb99f53f350536aed31b34540f86dfc5707dbe9173c8e59d3
+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": 384,
+  "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": 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_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": 128,
+  "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]"
+}