Added Model

0_Transformer/config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "indobenchmark/indobert-lite-base-p1",
+  "_num_labels": 5,
+  "architectures": [
+    "AlbertModel"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

0_Transformer/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:694ff51abc4465cd22dd7945e017a061c354d34e547f6feb4558fc5afaa49db2
+size 46747263

0_Transformer/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 32,
+  "do_lower_case": false
+}

0_Transformer/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

0_Transformer/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": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

1_Pooling/config.json

@@ -0,0 +1,9 @@
+{
+  "word_embedding_dimension": 768,
+  "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
+}

2_Dense/config.json

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

2_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad2363388c666f7378e908cbddaacf912aa19a4a943cb2b22ef7ff64d8744e73
+size 2363583

README.md

@@ -1,3 +1,91 @@
 ---
-license: apache-2.0
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+datasets:
+  - LazarusNLP/wikipedia_id_20230520
 ---
+
+# LazarusNLP/congen-indobert-lite-base
+
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 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('LazarusNLP/congen-indobert-lite-base')
+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=LazarusNLP/congen-indobert-lite-base)
+
+
+## Training
+The model was trained with the parameters:
+
+**DataLoader**:
+
+`torch.utils.data.dataloader.DataLoader` of length 6524 with parameters:
+```
+{'batch_size': 128, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers_congen.losses.ConGenLoss.ConGenLoss` 
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 20,
+    "evaluation_steps": 0,
+    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'transformers.optimization.AdamW'>",
+    "optimizer_params": {
+        "correct_bias": false,
+        "eps": 1e-06,
+        "lr": 0.0003
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 13048,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 32, 'do_lower_case': False}) with Transformer model: AlbertModel 
+  (1): Pooling({'word_embedding_dimension': 768, '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})
+  (2): Dense({'in_features': 768, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "1.0.0",
+    "transformers": "4.29.2",
+    "pytorch": "2.0.1+cu117"
+  }
+}

eval/similarity_evaluation_results.csv

@@ -0,0 +1,17 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,-1,0.7784628369715322,0.790441310186935,0.7745610761786144,0.7815123112306533,0.7707112402507581,0.7782807840320607,0.5110618110023735,0.5106208643865392
+1,-1,0.7919183217313387,0.8026935090405058,0.7781612660393912,0.7846604995944839,0.7743678045260972,0.7816463913967416,0.49774579884752534,0.5083373628127001
+2,-1,0.8130861078714943,0.8199870662006165,0.7644937862950276,0.7692507983083728,0.7609452213447676,0.7667759406867635,0.5105255947994755,0.5181236204472818
+3,-1,0.8120522841233425,0.8186837188637932,0.7569514053881609,0.7617098701664707,0.7537653246203407,0.759006221670444,0.4860231165617469,0.48471249955484075
+4,-1,0.8096698438029456,0.8176057439253992,0.7539490531181825,0.7601980534739224,0.7500700790213375,0.7570742790234226,0.49307098290290635,0.4970878479418517
+5,-1,0.8154446573476172,0.8221920403048152,0.7607869736755386,0.765150446235885,0.756842552092023,0.7624013379497931,0.5052868003959904,0.5053055818128606
+6,-1,0.8182260791503786,0.8240742902576491,0.7665322890312545,0.7723289417405284,0.7628382123508297,0.7697840965226919,0.5052775802370709,0.5092274902133616
+7,-1,0.8226442739407788,0.8281965374756299,0.7583215259849425,0.7619723412052115,0.7539303731069449,0.7589825319368873,0.5147085467217847,0.5215022704627538
+8,-1,0.8250791879929443,0.8302767883248077,0.767164179868101,0.7722566865545311,0.7637886454196815,0.7697028626849216,0.5251239718953331,0.5280571824538515
+9,-1,0.8175180934127748,0.8236161902306005,0.75219688988271,0.7588720365221943,0.7483920597915993,0.7562650335719203,0.48908222053279615,0.4938552834363178
+10,-1,0.8234490987201571,0.8291432428933043,0.7614318396464613,0.7668242716817875,0.7574953059572305,0.7635380611733849,0.5060344154344832,0.5059956103090336
+11,-1,0.818128634922896,0.824645219560505,0.755939003935069,0.7634814034489885,0.7516300329176759,0.7599805112910322,0.47717241436727775,0.48320670136398697
+12,-1,0.8235165732186087,0.8285989043600063,0.7532804361204786,0.7614422436425015,0.7490167315723992,0.7585644847033318,0.500012271619837,0.5050206843701895
+13,-1,0.8261978317523195,0.8302346388233832,0.7599432436544662,0.765971799548841,0.7560932821503724,0.7629799226669498,0.5138222972304346,0.5201865738264096
+14,-1,0.8265272353853084,0.829494040339557,0.7501531520145648,0.7569895102802171,0.7458370306298866,0.7538350347403957,0.5115806205876149,0.5194403704651349
+15,-1,0.824367971815316,0.8292325703701074,0.7494784306248647,0.7560956491103782,0.7452161064402848,0.7529456611154134,0.5088827882953869,0.5160813717087587

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "0_Transformer",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Dense",
+    "type": "sentence_transformers.models.Dense"
+  }
+]