Add new SentenceTransformer model.

.gitattributes

@@ -33,3 +33,12 @@ 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
+2_Asym/140225464236784_Dense/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+2_Asym/140228101622896_Dense/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+2_Asym/140225464235392_Dense/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+2_Asym/140225464235968_Dense/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+2_Asym/140225464223632_Dense/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+2_Asym/140225464236064_Dense/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+2_Asym/140225464231312_Dense/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+2_Asym/140225464232416_Dense/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

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
+}

2_Asym/140225464223632_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 1024, "out_features": 2048, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}

2_Asym/140225464223632_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e09d27f6e37e79b5889f99320b29eab442407414661f86706af8946f783d0239
+size 8398460

2_Asym/140225464231312_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 2048, "out_features": 2048, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}

2_Asym/140225464231312_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75db6e76d6b5838f1cd255ba48a1fffb13b807985583df180effbfb73abbfc92
+size 16787068

2_Asym/140225464232416_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 2048, "out_features": 1024, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}

2_Asym/140225464232416_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f73d9d5ee30e1c9c367620f4b32b59133841a9aa66c34c213c4eceeed1d91739
+size 8394364

2_Asym/140225464233232_Dropout/config.json

@@ -0,0 +1 @@
+{"dropout": 0.1}

2_Asym/140225464235392_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 2048, "out_features": 2048, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}

2_Asym/140225464235392_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53306f081b130f877d2d20e684b403951a08cf410c6854f2fc23f49427d5ba85
+size 16787068

2_Asym/140225464235968_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 2048, "out_features": 1024, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}

2_Asym/140225464235968_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:762e434b5b7dcfef9ae42841a4193578ecb74d750c5efa5433fd0b129883511f
+size 8394364

2_Asym/140225464236064_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 2048, "out_features": 2048, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}

2_Asym/140225464236064_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7cc7b864e5a7d41a179fa8660606d0d65e7a0ae3a3ac2076b810ee07234861c
+size 16787068

2_Asym/140225464236784_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 1024, "out_features": 2048, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}

2_Asym/140225464236784_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2759d8139196720ab46d120d3225231d160bd9fa74f39d7f59bab8a447155db
+size 8398460

2_Asym/140225507851568_Dropout/config.json

@@ -0,0 +1 @@
+{"dropout": 0.1}

2_Asym/140228101622896_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 2048, "out_features": 2048, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}

2_Asym/140228101622896_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c82ba0624007b1e5b7f281fdafa92e7106f7c7f954de0617fcf3ff261bd154f
+size 16787068

2_Asym/config.json

@@ -0,0 +1,37 @@
+{
+  "types": {
+    "140225464236784_Dense": "sentence_transformers.models.Dense",
+    "140228101622896_Dense": "sentence_transformers.models.Dense",
+    "140225507851568_Dropout": "sentence_transformers.models.Dropout",
+    "140225464235392_Dense": "sentence_transformers.models.Dense",
+    "140225464235968_Dense": "sentence_transformers.models.Dense",
+    "140225464231168_Normalize": "sentence_transformers.models.Normalize",
+    "140225464223632_Dense": "sentence_transformers.models.Dense",
+    "140225464236064_Dense": "sentence_transformers.models.Dense",
+    "140225464233232_Dropout": "sentence_transformers.models.Dropout",
+    "140225464231312_Dense": "sentence_transformers.models.Dense",
+    "140225464232416_Dense": "sentence_transformers.models.Dense",
+    "140225464235536_Normalize": "sentence_transformers.models.Normalize"
+  },
+  "structure": {
+    "dialog": [
+      "140225464236784_Dense",
+      "140228101622896_Dense",
+      "140225507851568_Dropout",
+      "140225464235392_Dense",
+      "140225464235968_Dense",
+      "140225464231168_Normalize"
+    ],
+    "fact": [
+      "140225464223632_Dense",
+      "140225464236064_Dense",
+      "140225464233232_Dropout",
+      "140225464231312_Dense",
+      "140225464232416_Dense",
+      "140225464235536_Normalize"
+    ]
+  },
+  "parameters": {
+    "allow_empty_key": false
+  }
+}

README.md

@@ -0,0 +1,106 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+
+---
+
+# diwank/dfe-large-en-2
+
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 2048 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('diwank/dfe-large-en-2')
+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=diwank/dfe-large-en-2)
+
+
+## Training
+The model was trained with the parameters:
+
+**DataLoader**:
+
+`torch.utils.data.dataloader.DataLoader` of length 3633 with parameters:
+```
+{'batch_size': 1024, '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": 4,
+    "evaluation_steps": 2000,
+    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'lion_pytorch.lion_pytorch.Lion'>",
+    "optimizer_params": {
+        "lr": 0.0001,
+        "weight_decay": 0.01
+    },
+    "scheduler": "WarmupCosine",
+    "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})
+  (2): Asym(
+    (dialog-0): Dense({'in_features': 1024, 'out_features': 2048, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+    (dialog-1): Dense({'in_features': 2048, 'out_features': 2048, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+    (dialog-2): Dropout(
+      (dropout_layer): Dropout(p=0.1, inplace=False)
+    )
+    (dialog-3): Dense({'in_features': 2048, 'out_features': 2048, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+    (dialog-4): Dense({'in_features': 2048, 'out_features': 1024, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+    (dialog-5): Normalize()
+    (fact-0): Dense({'in_features': 1024, 'out_features': 2048, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+    (fact-1): Dense({'in_features': 2048, 'out_features': 2048, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+    (fact-2): Dropout(
+      (dropout_layer): Dropout(p=0.1, inplace=False)
+    )
+    (fact-3): Dense({'in_features': 2048, 'out_features': 2048, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+    (fact-4): Dense({'in_features': 2048, 'out_features': 1024, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+    (fact-5): Normalize()
+  )
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "[CLS]": 101,
+  "[MASK]": 103,
+  "[PAD]": 0,
+  "[SEP]": 102,
+  "[UNK]": 100
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "/root/.cache/torch/sentence_transformers/BAAI_bge-large-en-v1.5/",
+  "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": "4.34.0",
+  "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"
+  }
+}

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_Asym",
+    "type": "sentence_transformers.models.Asym"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b4674c2135c4571743ae1c8ac2c8aa857cfdbd69eb18ecc2f39b57063463452
+size 1340699814

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 +1,58 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "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]"
+}