Add new SentenceTransformer model.

.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
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,9 @@
+{
+  "word_embedding_dimension": 1024,
+  "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

@@ -0,0 +1,129 @@
+---
+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
+
+
+#Mean Pooling - Take attention mask into account for correct averaging
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+
+
+# 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, mean pooling.
+sentence_embeddings = mean_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 75 with parameters:
+```
+{'batch_size': 4, '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": 10,
+    "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": 75,
+    "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': 1024, '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})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "WhereIsAI/UAE-Large-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": "4.33.3",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.33.3",
+    "pytorch": "2.1.0+cu118"
+  }
+}

eval/Information-Retrieval_evaluation_results.csv

@@ -0,0 +1,21 @@
+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
+0,50,0.92,0.94,0.97,0.97,0.92,0.92,0.3133333333333333,0.94,0.19399999999999995,0.97,0.09699999999999998,0.97,0.9348333333333333,0.9433531192611393,0.936996794871795,0.91,0.93,0.96,0.99,0.91,0.91,0.30999999999999994,0.93,0.19199999999999995,0.96,0.09899999999999999,0.99,0.9265277777777777,0.9410994187131007,0.9269625603864733
+0,-1,0.9,0.93,0.95,0.98,0.9,0.9,0.30999999999999994,0.93,0.18999999999999997,0.95,0.09799999999999998,0.98,0.9222619047619047,0.935874757101945,0.9236057782796914,0.88,0.93,0.95,0.97,0.88,0.88,0.30999999999999994,0.93,0.18999999999999997,0.95,0.09699999999999998,0.97,0.9094444444444446,0.9241137955963317,0.9118370518370519
+1,50,0.89,0.93,0.96,0.98,0.89,0.89,0.30999999999999994,0.93,0.19199999999999995,0.96,0.09799999999999999,0.98,0.9192500000000001,0.9337645464077078,0.9205833333333332,0.91,0.95,0.95,0.96,0.91,0.91,0.31666666666666665,0.95,0.18999999999999997,0.95,0.09599999999999997,0.96,0.9297619047619047,0.9372612259404771,0.9330800865800866
+1,-1,0.92,0.94,0.94,0.99,0.92,0.92,0.3133333333333333,0.94,0.18799999999999997,0.94,0.09899999999999999,0.99,0.9350793650793652,0.9475586359867411,0.9359126984126983,0.9,0.94,0.95,0.98,0.9,0.9,0.3133333333333333,0.94,0.18999999999999997,0.95,0.09799999999999999,0.98,0.9245119047619048,0.9376132885522472,0.926254329004329
+2,50,0.92,0.93,0.95,0.98,0.92,0.92,0.30999999999999994,0.93,0.18999999999999997,0.95,0.09799999999999999,0.98,0.9334682539682541,0.9441615578121003,0.9352106782106782,0.9,0.93,0.95,0.99,0.9,0.9,0.30999999999999994,0.93,0.18999999999999997,0.95,0.09899999999999999,0.99,0.9251349206349208,0.9403422247546098,0.9258492063492063
+2,-1,0.91,0.93,0.95,0.99,0.91,0.91,0.30999999999999994,0.93,0.18999999999999997,0.95,0.09899999999999999,0.99,0.9297182539682539,0.9436255041156724,0.9305515873015874,0.9,0.93,0.94,0.98,0.9,0.9,0.30999999999999994,0.93,0.18799999999999997,0.94,0.09799999999999999,0.98,0.9235119047619048,0.9368467840312288,0.9251902264402264
+3,50,0.91,0.93,0.95,0.99,0.91,0.91,0.30999999999999994,0.93,0.18999999999999997,0.95,0.09899999999999999,0.99,0.9292777777777778,0.9432373205795546,0.9301111111111111,0.9,0.93,0.94,0.98,0.9,0.9,0.30999999999999994,0.93,0.18799999999999997,0.94,0.09799999999999999,0.98,0.9232738095238094,0.9366180454934817,0.9248763736263735
+3,-1,0.91,0.93,0.94,0.99,0.91,0.91,0.30999999999999994,0.93,0.18799999999999997,0.94,0.09899999999999999,0.99,0.9289444444444445,0.9429308643782894,0.9297777777777777,0.9,0.93,0.94,0.98,0.9,0.9,0.30999999999999994,0.93,0.18799999999999997,0.94,0.09799999999999999,0.98,0.9232738095238094,0.9366180454934817,0.9248763736263735
+4,50,0.91,0.93,0.94,0.99,0.91,0.91,0.30999999999999994,0.93,0.18799999999999997,0.94,0.09899999999999999,0.99,0.928595238095238,0.9425824741470816,0.9294285714285714,0.9,0.93,0.94,0.98,0.9,0.9,0.30999999999999994,0.93,0.18799999999999997,0.94,0.09799999999999999,0.98,0.9228174603174604,0.9361506633055708,0.9244200244200245
+4,-1,0.91,0.93,0.94,0.99,0.91,0.91,0.30999999999999994,0.93,0.18799999999999997,0.94,0.09899999999999999,0.99,0.9282182539682539,0.9422093867981173,0.9290515873015872,0.89,0.93,0.94,0.98,0.89,0.89,0.30999999999999994,0.93,0.18799999999999997,0.94,0.09799999999999999,0.98,0.9178174603174604,0.9324599608412855,0.9194200244200245
+5,50,0.91,0.93,0.94,0.98,0.91,0.91,0.30999999999999994,0.93,0.18799999999999997,0.94,0.09799999999999999,0.98,0.9269007936507937,0.9389957051582448,0.9286432178932178,0.88,0.93,0.94,0.98,0.88,0.88,0.30999999999999994,0.93,0.18799999999999997,0.94,0.09799999999999999,0.98,0.9128174603174604,0.928769258377,0.9144200244200245
+5,-1,0.91,0.93,0.94,0.98,0.91,0.91,0.30999999999999994,0.93,0.18799999999999997,0.94,0.09799999999999999,0.98,0.9269007936507937,0.9389957051582448,0.9285674603174603,0.88,0.93,0.94,0.98,0.88,0.88,0.30999999999999994,0.93,0.18799999999999997,0.94,0.09799999999999999,0.98,0.912638888888889,0.928590573811524,0.9142414529914531
+6,50,0.89,0.93,0.94,0.98,0.89,0.89,0.30999999999999994,0.93,0.18799999999999997,0.94,0.09799999999999999,0.98,0.9169007936507937,0.931614300229674,0.9185674603174603,0.87,0.93,0.94,0.98,0.87,0.87,0.30999999999999994,0.93,0.18799999999999997,0.94,0.09799999999999999,0.98,0.9074007936507936,0.9246711328094918,0.9090033577533577
+6,-1,0.89,0.93,0.94,0.98,0.89,0.89,0.30999999999999994,0.93,0.18799999999999997,0.94,0.09799999999999999,0.98,0.9169007936507937,0.931614300229674,0.9185674603174603,0.87,0.93,0.94,0.98,0.87,0.87,0.30999999999999994,0.93,0.18799999999999997,0.94,0.09799999999999999,0.98,0.9072619047619048,0.9245267839982741,0.9088644688644688
+7,50,0.89,0.93,0.94,0.98,0.89,0.89,0.30999999999999994,0.93,0.18799999999999997,0.94,0.09799999999999999,0.98,0.9169007936507937,0.931614300229674,0.9185674603174603,0.87,0.93,0.94,0.98,0.87,0.87,0.30999999999999994,0.93,0.18799999999999997,0.94,0.09799999999999999,0.98,0.9071507936507937,0.9244071323048132,0.9087533577533579
+7,-1,0.89,0.93,0.94,0.98,0.89,0.89,0.30999999999999994,0.93,0.18799999999999997,0.94,0.09799999999999999,0.98,0.9169007936507937,0.931614300229674,0.9185674603174603,0.87,0.93,0.94,0.98,0.87,0.87,0.30999999999999994,0.93,0.18799999999999997,0.94,0.09799999999999999,0.98,0.9071507936507937,0.9244071323048132,0.9087533577533579
+8,50,0.89,0.93,0.94,0.98,0.89,0.89,0.30999999999999994,0.93,0.18799999999999997,0.94,0.09799999999999999,0.98,0.9169007936507937,0.931614300229674,0.9185674603174603,0.87,0.94,0.94,0.97,0.87,0.87,0.3133333333333333,0.94,0.18799999999999997,0.94,0.09699999999999998,0.97,0.9068730158730159,0.9220900667674394,0.9093846708846709
+8,-1,0.89,0.93,0.94,0.98,0.89,0.89,0.30999999999999994,0.93,0.18799999999999997,0.94,0.09799999999999999,0.98,0.9169007936507937,0.931614300229674,0.9185674603174603,0.87,0.94,0.94,0.97,0.87,0.87,0.3133333333333333,0.94,0.18799999999999997,0.94,0.09699999999999998,0.97,0.9068730158730159,0.9220900667674394,0.9093846708846709
+9,50,0.89,0.93,0.94,0.98,0.89,0.89,0.30999999999999994,0.93,0.18799999999999997,0.94,0.09799999999999999,0.98,0.9169007936507937,0.931614300229674,0.9185674603174603,0.87,0.94,0.94,0.97,0.87,0.87,0.3133333333333333,0.94,0.18799999999999997,0.94,0.09699999999999998,0.97,0.9068730158730159,0.9220900667674394,0.9093846708846709
+9,-1,0.89,0.93,0.94,0.98,0.89,0.89,0.30999999999999994,0.93,0.18799999999999997,0.94,0.09799999999999999,0.98,0.9169007936507937,0.931614300229674,0.9185674603174603,0.87,0.94,0.94,0.97,0.87,0.87,0.3133333333333333,0.94,0.18799999999999997,0.94,0.09699999999999998,0.97,0.9068730158730159,0.9220900667674394,0.9093846708846709

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:a22a9ec99f80c62d220ae9dfa1b6eac46a2cca481f079719a649a85f908f04e4
+size 1340699814

sentence_bert_config.json

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

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 +1,57 @@
+{
+  "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]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}