feat: Checkpoint 13800

Signed-off-by: Julep Developers <developers@julep.ai>

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,100 @@
+---
+license: mit
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+
+---
+
+# dfe-base-en
+
+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('julep-ai/dfe-base-en')
+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 1321 with parameters:
+```
+{'batch_size': 1280, '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": 12,
+    "evaluation_steps": 0,
+    "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 -->

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/140654129191936_Dense/config.json

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

2_Asym/140654129191936_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:208eed2d63c776a137954ad8290e40ee91432754ec07b1fc70a4ddc890f66cb3
+size 4726396

2_Asym/140654129198896_Dense/config.json

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

2_Asym/140654129198896_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8487aeba9cac38fbca92f3bdb0da88819f2de264508a80ff71388c280551665d
+size 9444988

2_Asym/140654129199328_Dense/config.json

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

2_Asym/140654129199328_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4eb147f91d745c0a5602afaf50254a57b010021b0114aad9cfc4acdf8514122
+size 4723324

2_Asym/140654129199376_Dense/config.json

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

2_Asym/140654129199376_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfdacf5a19b33b11cd1877386edf20e13a0b1e818caf00ec864e19e2324bebfe
+size 4723324

2_Asym/140654129388880_Dense/config.json

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

2_Asym/140654129388880_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6983a97e93899db94b23a77a425790d7aadb48ba0fbaf9dbcda453854fbe38a
+size 4726396

2_Asym/140663133264320_Dense/config.json

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

2_Asym/140663133264320_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4afe1d4cb3d88f6b9492a17917199940594a99ba4571f0e530ce15858cc9bc16
+size 9444988

2_Asym/config.json

@@ -0,0 +1,25 @@
+{
+  "types": {
+    "140654129388880_Dense": "sentence_transformers.models.Dense",
+    "140663133264320_Dense": "sentence_transformers.models.Dense",
+    "140654129199328_Dense": "sentence_transformers.models.Dense",
+    "140654129191936_Dense": "sentence_transformers.models.Dense",
+    "140654129198896_Dense": "sentence_transformers.models.Dense",
+    "140654129199376_Dense": "sentence_transformers.models.Dense"
+  },
+  "structure": {
+    "dialog": [
+      "140654129388880_Dense",
+      "140663133264320_Dense",
+      "140654129199328_Dense"
+    ],
+    "fact": [
+      "140654129191936_Dense",
+      "140654129198896_Dense",
+      "140654129199376_Dense"
+    ]
+  },
+  "parameters": {
+    "allow_empty_key": false
+  }
+}

README.md

@@ -1,3 +1,100 @@
 ---
 license: mit
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+
 ---
+
+# dfe-base-en
+
+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('julep-ai/dfe-base-en')
+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 1321 with parameters:
+```
+{'batch_size': 1280, '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": 12,
+    "evaluation_steps": 0,
+    "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 -->

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "/root/.cache/torch/sentence_transformers/BAAI_bge-base-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": 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": "4.33.2",
+  "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/triplet_evaluation_results-checkpoint.csv

@@ -0,0 +1,2 @@
+epoch,steps,accuracy_cosinus,accuracy_manhattan,accuracy_euclidean
+0,-1,0.8347865504093006,0.835933125349972,0.8326267231954777

eval/triplet_evaluation_results.csv

@@ -0,0 +1,11 @@
+epoch,steps,accuracy_cosinus,accuracy_manhattan,accuracy_euclidean
+0,-1,0.8347865504093006,0.835933125349972,0.8326267231954777
+1,-1,0.9147801509212596,0.9147534863877557,0.9126469882409407
+2,-1,0.9442177959096606,0.943391195371037,0.9422179558968616
+3,-1,0.9552035837133029,0.954990267445271,0.9536837053035757
+4,-1,0.9626429885609151,0.9630696210969789,0.9617097298882756
+5,-1,0.9655494227128496,0.9658960616484015,0.964962802975762
+6,-1,0.9678425725941925,0.9678159080606885,0.9675225981921446
+7,-1,0.9697890835399835,0.9693624510039197,0.9691757992693918
+8,-1,0.9714422846172306,0.9709889875476628,0.9706423486121111
+9,-1,0.9715756072847506,0.9718155880862864,0.9720022398208144

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 sha256:0902de760f1af733e3064489c15700f0658c2d955fcf9784b40069791cfef97a
+size 437996134

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 +1,15 @@
+{
+  "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]"
+}