Adds files

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false
+}

README.md

@@ -0,0 +1,126 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+
+---
+
+# {MODEL_NAME}
+
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 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)
+```
+
+
+
+## Usage (HuggingFace Transformers)
+Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
+
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+
+def cls_pooling(model_output, attention_mask):
+    return model_output[0][:,0]
+
+
+# Sentences we want sentence embeddings for
+sentences = ['This is an example sentence', 'Each sentence is converted']
+
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
+model = AutoModel.from_pretrained('{MODEL_NAME}')
+
+# Tokenize sentences
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+
+# Compute token embeddings
+with torch.no_grad():
+    model_output = model(**encoded_input)
+
+# Perform pooling. In this case, cls pooling.
+sentence_embeddings = cls_pooling(model_output, encoded_input['attention_mask'])
+
+print("Sentence embeddings:")
+print(sentence_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 707 with parameters:
+```
+{'batch_size': 40, 'sampler': 'torch.utils.data.sampler.RandomSampler', '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": 10,
+    "evaluation_steps": 0,
+    "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": 100,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "/root/.cache/torch/sentence_transformers/llmrails_ember-v1/",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.28.1",
+    "pytorch": "1.13.0+cu117"
+  }
+}

eval/.ipynb_checkpoints/Information-Retrieval_evaluation_results-checkpoint.csv

@@ -0,0 +1,2 @@
+epoch,steps,cos_sim-Accuracy@2,cos_sim-Accuracy@3,cos_sim-Precision@2,cos_sim-Recall@2,cos_sim-Precision@3,cos_sim-Recall@3,cos_sim-MRR@2,cos_sim-MRR@3,cos_sim-NDCG@2,cos_sim-NDCG@3,cos_sim-MAP@2,cos_sim-MAP@3,dot_score-Accuracy@2,dot_score-Accuracy@3,dot_score-Precision@2,dot_score-Recall@2,dot_score-Precision@3,dot_score-Recall@3,dot_score-MRR@2,dot_score-MRR@3,dot_score-NDCG@2,dot_score-NDCG@3,dot_score-MAP@2,dot_score-MAP@3
+0,-1,0.786,0.836,0.725,0.41561682557208873,0.632,0.5025919050247998,0.761,0.7776666666666665,0.7274892382408401,0.7234027733369421,0.7125,0.6920555555555555,0.798,0.842,0.728,0.4199918255720887,0.6273333333333333,0.5010919050247997,0.768,0.7826666666666665,0.7302629438553092,0.7215898868321315,0.713,0.6884444444444444

eval/Information-Retrieval_evaluation_results.csv

@@ -0,0 +1,11 @@
+epoch,steps,cos_sim-Accuracy@2,cos_sim-Accuracy@3,cos_sim-Precision@2,cos_sim-Recall@2,cos_sim-Precision@3,cos_sim-Recall@3,cos_sim-MRR@2,cos_sim-MRR@3,cos_sim-NDCG@2,cos_sim-NDCG@3,cos_sim-MAP@2,cos_sim-MAP@3,dot_score-Accuracy@2,dot_score-Accuracy@3,dot_score-Precision@2,dot_score-Recall@2,dot_score-Precision@3,dot_score-Recall@3,dot_score-MRR@2,dot_score-MRR@3,dot_score-NDCG@2,dot_score-NDCG@3,dot_score-MAP@2,dot_score-MAP@3
+0,-1,0.786,0.836,0.725,0.41561682557208873,0.632,0.5025919050247998,0.761,0.7776666666666665,0.7274892382408401,0.7234027733369421,0.7125,0.6920555555555555,0.798,0.842,0.728,0.4199918255720887,0.6273333333333333,0.5010919050247997,0.768,0.7826666666666665,0.7302629438553092,0.7215898868321315,0.713,0.6884444444444444
+1,-1,0.792,0.844,0.722,0.4120584922387554,0.6253333333333333,0.5017419050247998,0.769,0.786333333333333,0.7274310652527419,0.7214298121189583,0.7105,0.6867222222222221,0.794,0.854,0.715,0.41153349223875535,0.6233333333333334,0.49912523835813305,0.764,0.7839999999999998,0.7192995933250874,0.7161653355461067,0.7,0.6788333333333334
+2,-1,0.792,0.834,0.723,0.41603349223875535,0.624,0.49796690502479973,0.769,0.7829999999999999,0.7282047708672111,0.7196515586578535,0.7115,0.6868333333333334,0.784,0.834,0.721,0.41703349223875535,0.622,0.49793357169146646,0.761,0.7776666666666664,0.7248470045540256,0.7167630710706907,0.7095,0.6841111111111111
+3,-1,0.79,0.832,0.718,0.40955015890542207,0.6226666666666666,0.4977335716914664,0.764,0.7779999999999998,0.7225258877106183,0.7163430927842974,0.705,0.6825,0.776,0.83,0.706,0.4021334922387554,0.6193333333333333,0.4941002383581331,0.761,0.7789999999999998,0.7150517754212367,0.7133938756354776,0.6985,0.6786666666666668
+4,-1,0.788,0.832,0.72,0.4083168255720887,0.624,0.4968002383581331,0.766,0.7806666666666666,0.7254310652527419,0.718241191059222,0.709,0.6845,0.78,0.822,0.713,0.406500158905422,0.6153333333333333,0.48854190502479977,0.763,0.7769999999999999,0.7204677147225202,0.7108012281050157,0.7045,0.6773888888888889
+5,-1,0.794,0.842,0.716,0.41035849223875537,0.622,0.49775023835813303,0.762,0.7779999999999999,0.7191681213974328,0.7146432262568708,0.7,0.6785555555555556,0.794,0.842,0.713,0.409150158905422,0.616,0.4938057939136887,0.769,0.7849999999999998,0.7200151259514584,0.7126128614760423,0.7005,0.6751666666666665
+6,-1,0.776,0.82,0.705,0.40117238112764425,0.612,0.4905696828025775,0.755,0.7696666666666665,0.7115625371803966,0.7058558458165342,0.6945,0.6716666666666666,0.782,0.82,0.707,0.40187238112764423,0.6093333333333334,0.48663079391368863,0.759,0.7716666666666665,0.7135625371803966,0.7040330941931987,0.6955,0.6694444444444444
+7,-1,0.774,0.828,0.71,0.4034501589054221,0.614,0.49326412724702196,0.752,0.7699999999999998,0.7145258877106182,0.7075484037989945,0.699,0.6727777777777777,0.778,0.826,0.711,0.4061168255720887,0.614,0.4934307939136886,0.755,0.7709999999999999,0.7157521820961493,0.7083807661100918,0.6995,0.6739444444444443
+8,-1,0.786,0.816,0.717,0.40840015890542203,0.614,0.48805579391368864,0.766,0.7759999999999999,0.7235625371803965,0.7105357528291434,0.707,0.6781111111111111,0.784,0.818,0.71,0.4055057144609776,0.6146666666666666,0.48976412724702195,0.764,0.7753333333333332,0.7176940091080513,0.7098669640688429,0.7,0.6768333333333333
+9,-1,0.786,0.828,0.71,0.4060057144609776,0.6173333333333333,0.4930641272470219,0.764,0.7779999999999999,0.7172414203369893,0.7122232228174816,0.699,0.6771111111111111,0.794,0.822,0.715,0.40917238112764426,0.614,0.4899807939136886,0.769,0.7783333333333333,0.7215625371803965,0.710337521081645,0.7025,0.6763888888888889

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74ad1b39955b087a6b578ba0db790af95707e28e16feda07e72d62cdc2a3022e
+size 1340699369

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": true
+}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

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": 512,
+  "model_max_length": 512,
+  "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]"
+}