First commit

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "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
+}

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "indobenchmark/indobert-base-p2",
+  "_num_labels": 5,
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "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": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50000
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.25.1",
+    "pytorch": "1.13.1+cu116"
+  }
+}

eval/similarity_evaluation_sts-dev_results.csv

@@ -0,0 +1,12 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,64,0.01889159788729281,0.016624999289029295,0.03469793378231501,0.017171827743118543,0.036318400873366054,0.018583970685317548,0.004526911551087426,0.0032431555058285238
+0,128,0.022875577846926422,0.02174170637990998,0.03954375146428044,0.022328548982320333,0.04091356539768457,0.023862140128058987,0.009440222942678963,0.009304684394661674
+0,192,0.01387889539267916,0.011667832952411703,0.032260116008321994,0.014945492615462254,0.033935165768639024,0.01645172093143081,-0.002182766960806109,-0.0017655002863984455
+0,256,0.01828523647538354,0.016341884358734068,0.036781238263772824,0.02040151949756355,0.03792863232775403,0.021215023956803376,0.00035982769085127144,-5.889061530307879e-05
+0,320,0.012641365631522607,0.011684845924611569,0.032758269647456324,0.01603228731714641,0.03382800484767004,0.016835889943854928,-0.0026152727867795895,-0.0012867775061407426
+0,384,0.014237791942630909,0.011397548550683043,0.032379164868574596,0.015113215221115445,0.03339659541400877,0.01596477329797923,-1.451163034025292e-05,0.0001286957913938935
+0,448,0.013316602487679833,0.010643519895732825,0.031116715761429405,0.014039553163540055,0.032519563320689275,0.01518211692168955,-0.0006667334600426175,-0.00047201737871873685
+0,512,0.012129810457018518,0.00915920347695669,0.030580314866465282,0.013329280142078249,0.031828637208115206,0.01423172931123735,-0.0019343597440829874,-0.002409726630392591
+0,576,0.012643408389483751,0.0099651818342994,0.03083155144046526,0.013689347205845947,0.03205055544312211,0.014569118519958601,-0.0014216084984591919,-0.0022294500998564252
+0,640,0.012239800823974158,0.009318939736809147,0.030432664638052977,0.013133601134857677,0.03166092534492111,0.014084817348849227,-0.001762226715672962,-0.0025439156403049275
+0,-1,0.012225819579360945,0.009298663370442524,0.030418787308967545,0.013091582733741967,0.031646576568198,0.014064586263107763,-0.0017720743898674263,-0.0025531051846128

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad1c6cf505822592f24f9736e75c48a0323cbc1d2233aa154dbf7380ce5c8f98
+size 497836589

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 75,
+  "do_lower_case": false
+}

similarity.py

@@ -0,0 +1,26 @@
+import torch
+from sentence_transformers import SentenceTransformer, util
+
+# Path to your model `.bin` file
+model_path = "pytorch_model.bin"
+
+# Path to your tokenizer `.json` file
+tokenizer_path = "tokenizer.json"
+
+# Load the model
+model = SentenceTransformer(model_path)
+
+# Load the tokenizer
+tokenizer = util.load_tokenizer(tokenizer_path)
+
+# Your sentences
+sentences = ["This is an example sentence", "Each sentence is converted"]
+
+# Preprocess the sentences using the tokenizer
+encoded_sentences = tokenizer.encode(sentences, batch_size=None, return_tensors="pt")
+
+# Get the embeddings from the model
+embeddings = model(encoded_sentences)
+
+# Print the embeddings
+print(embeddings)

similarity_evaluation_sts-test_results.csv

@@ -0,0 +1,4 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+-1,-1,0.012225819579360945,0.009298663370442524,0.030418787308967545,0.013091582733741967,0.031646576568198,0.014064586263107763,-0.0017720743898674263,-0.0025531051846128
+-1,-1,0.012225819579360945,0.009298663370442524,0.030418787308967545,0.013091582733741967,0.031646576568198,0.014064586263107763,-0.0017720743898674263,-0.0025531051846128
+-1,-1,0.022875577846926422,0.02174170637990998,0.03954375146428044,0.022328548982320333,0.04091356539768457,0.023862140128058987,0.009440222942678963,0.009304684394661674

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 +1,16 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "indobenchmark/indobert-base-p2",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--indobenchmark--indobert-base-p2/snapshots/94b4e0a82081fa57f227fcc2024d1ea89b57ac1f/special_tokens_map.json",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}