Upload folder using huggingface_hub

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
+}

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 1024 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': 1024, '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-large-japanese-v2",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "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": "4.28.1",
+  "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": 14848,
+  "best-dev": 79.89326362092076
+}

log.csv

@@ -0,0 +1,66 @@
+epoch,step,loss,sts-dev
+0,0,inf,46.70784718045186
+0,256,0.1804292798042297,52.72027437941158
+0,512,0.0020474940538406,54.16706057378039
+0,768,0.0009167678654193,54.97971089516359
+0,1024,0.000422166660428,55.25231988293338
+0,1280,0.0003259554505348,57.31856344751787
+0,1536,0.0002286350354552,58.87054645225247
+0,1792,0.0001499559730291,60.728810953166615
+0,2048,0.0001791073009371,61.57247985363832
+0,2304,0.0001186188310384,64.60548209276658
+0,2560,0.0001095095649361,63.10229448214084
+0,2816,0.0001485776156187,64.8266343938356
+0,3072,5.192495882511139e-05,64.93407974180886
+0,3328,5.085254088044167e-05,65.81752870539546
+0,3584,4.379916936159134e-05,67.45208926863944
+0,3840,4.599476233124733e-05,68.05788327988445
+0,4096,4.309089854359627e-05,69.45097516603441
+0,4352,3.668293356895447e-05,68.1476778494779
+0,4608,9.581120684742928e-05,69.92317914058378
+0,4864,2.981838770210743e-05,70.9661656639272
+0,5120,2.7928035706281665e-05,70.94022380977198
+0,5376,2.4954788386821747e-05,71.95443935736876
+0,5632,0.0002523055300116,64.31970216926345
+0,5888,8.713500574231148e-05,69.52938449247287
+0,6144,0.0014079879038035,70.47003750847361
+0,6400,0.000243455171585,71.59856983457301
+0,6656,0.000127900391817,74.68453275823876
+0,6912,0.0001000803895294,75.77340285188441
+0,7168,4.809629172086716e-05,76.39808954543045
+0,7424,7.226737216114998e-05,77.21090146846127
+0,7680,5.386536940932274e-05,77.35177080166082
+0,7936,6.202561780810356e-05,78.88216498082295
+0,8192,4.967162385582924e-05,78.44234060894145
+0,8448,8.730334229767323e-05,77.11248318696224
+0,8704,3.610621206462383e-05,77.38938397378755
+0,8960,3.122887574136257e-05,77.82144371150366
+0,9216,2.6472844183444977e-05,77.64439577421061
+0,9472,3.739865496754646e-05,77.82867263629335
+0,9728,6.275856867432594e-05,77.78532545057863
+0,9984,0.0001052424777299,77.68747091778894
+0,10240,6.868503987789154e-05,78.50513744745713
+0,10496,2.1886546164751053e-05,78.41693329853474
+0,10752,2.1351734176278114e-05,78.40869491745303
+0,11008,6.39175996184349e-05,77.34029669023184
+0,11264,2.041761763393879e-05,77.46689545708392
+0,11520,1.9822735339403152e-05,77.56863484544071
+0,11776,0.0001011767890304,76.97902467846677
+0,12032,1.891795545816421e-05,77.33079748604983
+0,12288,2.008024603128433e-05,77.43681879408709
+0,12544,1.6340520232915878e-05,77.87685933905435
+0,12800,1.8035294488072395e-05,78.98472505927285
+0,13056,1.5516066923737526e-05,79.37901670816368
+0,13312,1.7801765352487564e-05,79.09891287263548
+0,13568,1.2751086615025995e-05,79.24946296985583
+0,13824,2.7165631763637062e-05,79.63705481260891
+0,14080,9.27936052903533e-05,79.62363077978016
+0,14336,1.8229475244879723e-05,79.80480156914284
+0,14592,1.4328979887068272e-05,79.78896480741983
+0,14848,1.1875061318278313e-05,79.89326362092076
+0,15104,1.981784589588642e-05,79.06084666759766
+0,15360,1.3236538507044315e-05,79.40354417627844
+0,15616,4.09658532589674e-05,79.15875606571835
+1,15872,1.979898661375045e-05,79.18473415613285
+1,16128,4.3475418351590633e-05,79.22740284079154
+1,16384,1.6250647604465485e-05,79.1942526682348

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 sha256:16a74528fe4d664be1b409f3143180d40a61f9b854875fcfd193dc5e5bf3aee0
+size 1349897965

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": 79.61770842846016,
+  "jsts-val": 81.40370972668754,
+  "jsts-train": 77.77128665725087,
+  "avg": 79.59756827079953
+}

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"
+}