v1

Signed-off-by: Diwank Singh <[email protected]>

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/139759749869296_Dense/config.json

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

2_Asym/139759749869296_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81d2629d3ce8d0a4fc67587fb0faf12db9d5966fdfbc263caa061932c76823b8
+size 8394364

2_Asym/139759749870880_Dense/config.json

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

2_Asym/139759749870880_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd6694dc33f31d11d88a87da677f9755436b5fb522f73bec6b66ef0b94d097f2
+size 16787068

2_Asym/139759749873328_Dense/config.json

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

2_Asym/139759749873328_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:445a80966eabcd388789b825ae76c8b871d651582f103b57e968d2dd05eeca87
+size 8398460

2_Asym/139762386917776_Dense/config.json

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

2_Asym/139762386917776_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4beb5d580088294aaae0b2b32a87c55c18869c73c28d2f7de3ba029876a0abec
+size 8394364

2_Asym/139771065711008_Dense/config.json

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

2_Asym/139771065711008_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:979e712b7a332597434772b6e4841f72efc961e9057506693b8f5c740ca3771d
+size 16787068

2_Asym/139771065971808_Dense/config.json

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

2_Asym/139771065971808_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e81a915b1fa1aa031f582c7c2f4a8dad97e47bac27ff43701074266fe6bdf6d3
+size 8398460

2_Asym/139911174117776_Dense/config.json

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

2_Asym/139911174117776_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d802959f3b7009b25b6cd0ddd862c11d5aa3b8e34a49ca7519e6f580e965f9b7
+size 8394364

2_Asym/139911174118736_Dense/config.json

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

2_Asym/139911174118736_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff9a818c30f6cf3246002f7d48bbf88cb932f499a033b78a31fc2d8da69b8148
+size 8398460

2_Asym/139911174119600_Dense/config.json

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

2_Asym/139911174119600_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8618c4bf5eb623582cde02743035f0870c003bff36b753340ffe74b76e388e1
+size 8398460

2_Asym/139911174122624_Dense/config.json

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

2_Asym/139911174122624_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:060a7ad01cddc99f71e6bfe38f1269ec8374114eafcbd67c59d54a3bdf901f93
+size 16787068

2_Asym/139911174123152_Dense/config.json

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

2_Asym/139911174123152_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a9f8fd077b6796d110550914ce3390950e1909c56b5d134b7fe75a06f960bc4
+size 8394364

2_Asym/139913809775248_Dense/config.json

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

2_Asym/139913809775248_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a196cb53a82bd9a4a447c40314840c4917477e88f1b65e6b0f6872e0ad18744
+size 16787068

2_Asym/config.json

@@ -0,0 +1,29 @@
+{
+  "types": {
+    "139759749873328_Dense": "sentence_transformers.models.Dense",
+    "139771065711008_Dense": "sentence_transformers.models.Dense",
+    "139762386917776_Dense": "sentence_transformers.models.Dense",
+    "139762386917200_Normalize": "sentence_transformers.models.Normalize",
+    "139771065971808_Dense": "sentence_transformers.models.Dense",
+    "139759749870880_Dense": "sentence_transformers.models.Dense",
+    "139759749869296_Dense": "sentence_transformers.models.Dense",
+    "139759749864928_Normalize": "sentence_transformers.models.Normalize"
+  },
+  "structure": {
+    "dialog": [
+      "139759749873328_Dense",
+      "139771065711008_Dense",
+      "139762386917776_Dense",
+      "139762386917200_Normalize"
+    ],
+    "fact": [
+      "139771065971808_Dense",
+      "139759749870880_Dense",
+      "139759749869296_Dense",
+      "139759749864928_Normalize"
+    ]
+  },
+  "parameters": {
+    "allow_empty_key": false
+  }
+}

README.md

@@ -1,3 +1,98 @@
 ---
-license: mit
+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 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('{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 3633 with parameters:
+```
+{'batch_size': 1024, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.OnlineContrastiveLoss.OnlineContrastiveLoss` 
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 6,
+    "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): Dense({'in_features': 2048, 'out_features': 1024, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+    (dialog-3): 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): Dense({'in_features': 2048, 'out_features': 1024, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+    (fact-3): 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"
+  }
+}

eval/.ipynb_checkpoints/similarity_evaluation_results-checkpoint.csv

@@ -0,0 +1,2 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,200,0.09538986217734022,0.08384386662398645,0.09539623750199215,0.08382535432287805,0.036019534063834034,0.030707494752119608,0.09538948135965447,0.08383444891529954

eval/similarity_evaluation_results.csv

@@ -0,0 +1,11 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,200,0.09538986217734022,0.08384386662398645,0.09539623750199215,0.08382535432287805,0.036019534063834034,0.030707494752119608,0.09538948135965447,0.08383444891529954
+0,400,0.4715094507136195,0.5037850362310335,0.47538241497043077,0.5037851242199534,0.4938051360078945,0.5060080389239441,0.47150933344974283,0.5037850314478904
+0,2000,0.7228417329018256,0.7045284462973851,0.7416009762958347,0.7045286446661528,0.7294892059102114,0.7034054227606624,0.7228416863848557,0.704528494298767
+0,-1,0.7387045312329137,0.7114060466653345,0.7576018994493214,0.711405910689208,0.7441002517102357,0.7102147572542092,0.7387045555426008,0.7114061507099086
+1,2000,0.7445957522164166,0.7144410506640689,0.7632079551550423,0.7144408986857114,0.750044548143612,0.713377520008261,0.7445956500500408,0.7144408602956258
+1,-1,0.7403974962810842,0.7117442453449414,0.7592900426897151,0.7117442853401136,0.7462961412416763,0.7104840261620768,0.740397464607492,0.711744155778095
+2,2000,0.7412765003718448,0.7115736774299289,0.7595686820436869,0.7115736262673157,0.7469862005999004,0.7105323032569937,0.7412764378172917,0.7115734759134695
+2,-1,0.7390358779662405,0.7105991453607753,0.757392918167112,0.7105991038189222,0.7444325444223947,0.7094801004272172,0.7390358427716103,0.7105991229781184
+3,2000,0.7393006180821876,0.710289426944981,0.7576480853962786,0.7102894877307891,0.74440332435888,0.7092671328929592,0.7393005765997176,0.7102895181099055
+3,-1,0.7369147194033147,0.7091520824844612,0.7555130843201373,0.709152216865955,0.7421882753435206,0.7080979679445787,0.7369146918063216,0.7091522664624613

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]"
+}