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:
+- shunk031/jsnli
+---
+
+# {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": 64,
+  "best-dev": 84.35700372236889
+}

log.csv

@@ -0,0 +1,66 @@
+epoch,step,loss,sts-dev
+0,0,inf,46.72837224312097
+0,32,5.49169921875,79.31070160603963
+0,64,2.51708984375,84.35700372236889
+0,96,2.013916015625,82.41349585392163
+0,128,1.83056640625,80.40566982305087
+0,160,1.715576171875,77.84721366215935
+0,192,1.650146484375,78.6757653419235
+0,224,1.568115234375,73.42996624180068
+0,256,1.55322265625,75.57552162351263
+1,288,1.490966796875,71.41986682440324
+1,320,1.37548828125,73.29193104300393
+1,352,1.33544921875,72.80806281746437
+1,384,1.350830078125,72.77195292066885
+1,416,1.353759765625,69.87782142691363
+1,448,1.33447265625,64.9175102353748
+1,480,1.309326171875,69.45867633288623
+1,512,1.31982421875,70.6730909328148
+1,544,1.29150390625,70.64751383186746
+2,576,1.212646484375,65.82802791174757
+2,608,1.11669921875,66.64306435617323
+2,640,1.14453125,65.48764039746843
+2,672,1.1185302734375,66.58600028071007
+2,704,1.123779296875,67.64014437611549
+2,736,1.103759765625,69.60152425618847
+2,768,1.141357421875,69.34622506400544
+2,800,1.270263671875,70.32409725193519
+2,832,1.221435546875,67.92858244662744
+3,864,1.0614013671875,66.34717772523808
+3,896,1.0054931640625,66.87521082007706
+3,928,1.0040283203125,65.41458032481682
+3,960,1.0062255859375,65.70913894370779
+3,992,1.0181884765625,66.46946316417328
+3,1024,0.996337890625,63.34887069413857
+3,1056,1.02392578125,65.18104616486384
+3,1088,0.9970703125,64.49234957916627
+3,1120,1.0,64.80023992366682
+4,1152,0.884521484375,65.09789161785304
+4,1184,0.880615234375,66.50805762020076
+4,1216,0.886474609375,63.74224407082551
+4,1248,0.8818359375,63.54117456035738
+4,1280,0.8819580078125,65.77741134837758
+4,1312,0.883544921875,66.75449263267615
+4,1344,0.875732421875,63.99539291809667
+4,1376,0.9068603515625,64.31698278731722
+5,1408,0.8865966796875,65.00043435754733
+5,1440,0.7822265625,64.22602226609517
+5,1472,0.785400390625,64.0694313946185
+5,1504,0.7928466796875,63.40049229004234
+5,1536,0.784912109375,62.86333382743011
+5,1568,0.794189453125,64.06125094235347
+5,1600,0.810546875,62.99456391252577
+5,1632,0.8006591796875,62.3648377584635
+5,1664,0.7896728515625,64.00460895931644
+6,1696,0.7900390625,64.12996526496609
+6,1728,0.720703125,64.04989699764432
+6,1760,0.7353515625,62.60633883039293
+6,1792,0.735595703125,62.39235079765329
+6,1824,0.72314453125,62.836391633071166
+6,1856,0.7305908203125,63.51677689636537
+6,1888,0.729248046875,63.40423279523494
+6,1920,0.7313232421875,63.03712185206447
+6,1952,0.733154296875,63.04729553320853
+7,1984,0.699462890625,62.68467625961607
+7,2016,0.70556640625,62.67148071717765
+7,2048,0.69970703125,62.75529368448359

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:d8484e8d52ac2e6d9a263662ac4d11932518ee09ed7566ee43b9a044971fff71
+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": 83.05096544584796,
+  "jsts-val": 83.07326084142757,
+  "jsts-train": 79.61292079857638,
+  "avg": 81.91238236195063
+}

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"
+}