Upload folder using huggingface_hub

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
+}

README.md

@@ -0,0 +1,92 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+datasets:
+- wiki40b
+---
+
+# {MODEL_NAME}
+
+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('{MODEL_NAME}')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+
+
+## Usage (HuggingFace Transformers)
+Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
+
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+
+def cls_pooling(model_output, attention_mask):
+    return model_output[0][:,0]
+
+
+# Sentences we want sentence embeddings for
+sentences = ['This is an example sentence', 'Each sentence is converted']
+
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
+model = AutoModel.from_pretrained('{MODEL_NAME}')
+
+# Tokenize sentences
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+
+# Compute token embeddings
+with torch.no_grad():
+    model_output = model(**encoded_input)
+
+# Perform pooling. In this case, cls pooling.
+sentence_embeddings = cls_pooling(model_output, encoded_input['attention_mask'])
+
+print("Sentence embeddings:")
+print(sentence_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})
+
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) 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})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "cl-tohoku/bert-base-japanese-v3",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.28.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32768
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.28.1",
+    "pytorch": "2.0.1+cu118"
+  }
+}

dev-metrics.json

@@ -0,0 +1,5 @@
+{
+  "best-epoch": 0,
+  "best-step": 2816,
+  "best-dev": 79.14925054212402
+}

log.csv

@@ -0,0 +1,66 @@
+epoch,step,loss,sts-dev
+0,0,inf,51.37411795900895
+0,256,0.0375348776578903,55.5997536647364
+0,512,0.0017691701650619,58.32817940768812
+0,768,0.0006307438015937,59.3974185060456
+0,1024,0.0003144387155771,60.754689631552935
+0,1280,0.0004976624622941,67.08745072940616
+0,1536,0.0002566464245319,68.1524768645118
+0,1792,0.0002705361694097,69.40357586993056
+0,2048,0.0001239106059074,70.00059301214966
+0,2304,0.0003662584349513,75.31010320876732
+0,2560,0.0009017521515488,76.00143228736593
+0,2816,0.000157325528562,79.14925054212402
+0,3072,7.141055539250374e-05,79.03881731254904
+0,3328,6.363820284605026e-05,78.44641639262007
+0,3584,0.0003677839413285,69.92161167599382
+0,3840,0.0001026871614158,68.42750644636237
+0,4096,9.204680100083352e-05,70.72705620298922
+0,4352,0.0001523927785456,71.94724540351626
+0,4608,5.27617521584034e-05,73.47894342360826
+0,4864,0.0004469738341867,66.93028259965841
+0,5120,0.0005747117102146,62.61976106536561
+0,5376,9.74196009337902e-05,64.04559706437584
+0,5632,0.0015562903136014,69.92255616122571
+0,5888,0.0010261721909046,61.98660674368782
+0,6144,0.0001530339941382,63.50736446491301
+0,6400,8.464325219392776e-05,65.00607265185072
+0,6656,0.0001220507547259,64.11445092781186
+0,6912,7.890071719884872e-05,66.22976181708123
+0,7168,9.68356616795063e-05,65.92655281556975
+0,7424,8.580600842833519e-05,65.17092915065315
+0,7680,0.0001265667378902,65.30866918870973
+0,7936,6.173737347126007e-05,66.90631113844152
+0,8192,0.0001264261081814,66.40594180975687
+0,8448,0.0001129913143813,65.82487123637435
+0,8704,6.541237235069275e-05,66.07900519557332
+0,8960,3.945222124457359e-05,66.91985335070422
+0,9216,0.0003336034715175,60.87154559005693
+0,9472,6.768666207790375e-05,62.93127257528387
+0,9728,5.523348227143288e-05,62.83898335246322
+0,9984,0.0001294771209359,63.87235436545296
+0,10240,0.0001297239214181,71.55534428591778
+0,10496,5.560088902711868e-05,72.26094985542503
+0,10752,0.0002071415074169,67.9768502124699
+0,11008,7.525458931922913e-05,70.44867140163949
+0,11264,0.0001133475452661,73.38390697765232
+0,11520,8.798344060778618e-05,73.5864667379101
+0,11776,4.829838871955872e-05,73.398043540928
+0,12032,3.966083750128746e-05,73.17604312647413
+0,12288,0.000146017409861,73.03065062945811
+0,12544,0.0001280489377677,73.41318767441048
+0,12800,3.561563789844513e-05,72.99900370616899
+0,13056,3.670249134302139e-05,73.3663132648536
+0,13312,3.159511834383011e-05,73.28953413824371
+0,13568,3.014621324837208e-05,73.1532624579162
+0,13824,6.573181599378586e-05,72.19940893582316
+0,14080,2.860999666154385e-05,72.19998744238026
+0,14336,4.158122465014458e-05,71.95310234208006
+0,14592,2.8798123821616173e-05,72.24484132141129
+0,14848,6.46631233394146e-05,71.71260103237086
+0,15104,2.8088223189115524e-05,72.05196625094614
+0,15360,2.8930604457855225e-05,72.30732956907381
+0,15616,2.897414378821849e-05,72.5329350302894
+1,15872,2.837018109858036e-05,72.58699593041659
+1,16128,8.221296593546867e-05,72.68198072076807
+1,16384,2.6318710297346115e-05,72.70427711066239

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:b51be3aac3b2f84cc5fec4632604eec977c8a6c152a72d46368fed9e336f8110
+size 444897069

sentence_bert_config.json

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

special_tokens_map.json

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

sts-metrics.json

@@ -0,0 +1,6 @@
+{
+  "jsick": 79.01221347847088,
+  "jsts-val": 78.94769808578855,
+  "jsts-train": 74.47873985273404,
+  "avg": 77.47955047233116
+}

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "do_subword_tokenize": true,
+  "do_word_tokenize": true,
+  "jumanpp_kwargs": null,
+  "mask_token": "[MASK]",
+  "mecab_kwargs": {
+    "mecab_dic": "unidic_lite"
+  },
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "subword_tokenizer_type": "wordpiece",
+  "sudachi_kwargs": null,
+  "tokenizer_class": "BertJapaneseTokenizer",
+  "unk_token": "[UNK]",
+  "word_tokenizer_type": "mecab"
+}