Add new SentenceTransformer model.

.gitattributes

@@ -33,3 +33,6 @@ 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/140287552706576_Dense/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+2_Asym/140287552711232_Dense/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false
+}

2_Asym/140287552706000_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 1536, "out_features": 768, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}

2_Asym/140287552706000_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cd051b238404473aa098587f6a537ecd8a037343fdb990ef3b2ec7b883f69a1
+size 4723260

2_Asym/140287552706576_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 1536, "out_features": 1536, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}

2_Asym/140287552706576_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c19ee0f5758a48238877408de0abff021d7c1533184cffd0afaf35c81cb7a49
+size 9444924

2_Asym/140287552708112_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 768, "out_features": 1536, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}

2_Asym/140287552708112_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b5ab2a35a3d04a6f87be00a603854a2a2d495a33b60d697f5208cc4ba30f63c
+size 4726332

2_Asym/140287552711232_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 1536, "out_features": 1536, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}

2_Asym/140287552711232_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e69591ab79a7e14a9253bce50f6e785195c49fdc25421de798d6dabd4bf43c29
+size 9444924

2_Asym/140287552711952_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 1536, "out_features": 768, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}

2_Asym/140287552711952_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36c175636371340bb5b946ffeadfadf5525e2e0eb034f8aa3aefd77407db7ea5
+size 4723260

2_Asym/140296232737504_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 768, "out_features": 1536, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}

2_Asym/140296232737504_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4888045196afe8791f49212ad870ac1aef3999e6ea4a76e508ea8f3520dd3066
+size 4726332

2_Asym/config.json

@@ -0,0 +1,25 @@
+{
+  "types": {
+    "140296232737504_Dense": "sentence_transformers.models.Dense",
+    "140287552706576_Dense": "sentence_transformers.models.Dense",
+    "140287552711952_Dense": "sentence_transformers.models.Dense",
+    "140287552708112_Dense": "sentence_transformers.models.Dense",
+    "140287552711232_Dense": "sentence_transformers.models.Dense",
+    "140287552706000_Dense": "sentence_transformers.models.Dense"
+  },
+  "structure": {
+    "dialog": [
+      "140296232737504_Dense",
+      "140287552706576_Dense",
+      "140287552711952_Dense"
+    ],
+    "fact": [
+      "140287552708112_Dense",
+      "140287552711232_Dense",
+      "140287552706000_Dense"
+    ]
+  },
+  "parameters": {
+    "allow_empty_key": false
+  }
+}

README.md

@@ -0,0 +1,99 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+
+---
+
+# diwank/dfe-base-en-1
+
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1536 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-base-en-1')
+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-base-en-1)
+
+
+## Training
+The model was trained with the parameters:
+
+**DataLoader**:
+
+`torch.utils.data.dataloader.DataLoader` of length 2562 with parameters:
+```
+{'batch_size': 1320, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.TripletLoss.TripletLoss` with parameters:
+  ```
+  {'distance_metric': 'TripletDistanceMetric.EUCLIDEAN', 'triplet_margin': 5}
+  ```
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 6,
+    "evaluation_steps": 1500,
+    "evaluator": "sentence_transformers.evaluation.TripletEvaluator.TripletEvaluator",
+    "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': 768, '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': 768, 'out_features': 1536, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+    (dialog-1): Dense({'in_features': 1536, 'out_features': 1536, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+    (dialog-2): Dense({'in_features': 1536, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+    (fact-0): Dense({'in_features': 768, 'out_features': 1536, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+    (fact-1): Dense({'in_features': 1536, 'out_features': 1536, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+    (fact-2): Dense({'in_features': 1536, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+  )
+)
+```
+
+## 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": "./dfe-base-en/",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "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 sha256:9243b3c55db737a995b2b84b25be196463cbbd8a247063081f5582890754f317
+size 437993382

sentence_bert_config.json

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

special_tokens_map.json

@@ -0,0 +1,14 @@
+{
+  "additional_special_tokens": [
+    "[PAD]",
+    "[UNK]",
+    "[CLS]",
+    "[SEP]",
+    "[MASK]"
+  ],
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,71 @@
+{
+  "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": [
+    "[PAD]",
+    "[UNK]",
+    "[CLS]",
+    "[SEP]",
+    "[MASK]"
+  ],
+  "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]"
+}