Duplicate from llm-book/bert-base-japanese-v3-jsts

Co-authored-by: Ryokan Ri <ryo0634@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,42 @@
+---
+language:
+- ja
+license: apache-2.0
+library_name: transformers
+datasets:
+- llm-book/JGLUE
+---
+
+# bert-base-japanese-v3-jsts
+
+「[大規模言語モデル入門](https://www.amazon.co.jp/dp/4297136333)」の第5章で紹介している(意味類似度計算)のモデルです。
+[cl-tohoku/bert-base-japanese-v3](https://huggingface.co/cl-tohoku/bert-base-japanese-v3)を[JGLUE](https://huggingface.co/datasets/llm-book/JGLUE)のJSTSデータセットでファインチューニングして構築されています。
+
+## 関連リンク
+
+* [GitHubリポジトリ](https://github.com/ghmagazine/llm-book)
+* [Colabノートブック（訓練）](https://colab.research.google.com/github/ghmagazine/llm-book/blob/main/chapter5/5-4-sts-finetuning.ipynb)
+* [Colabノートブック（推論）](https://colab.research.google.com/github/ghmagazine/llm-book/blob/main/chapter5/5-4-sts-analysis.ipynb)
+* [データセット](https://huggingface.co/datasets/llm-book/JGLUE)
+* [大規模言語モデル入門（Amazon.co.jp）](https://www.amazon.co.jp/dp/4297136333/)
+* [大規模言語モデル入門（gihyo.jp）](https://gihyo.jp/book/2023/978-4-297-13633-8)
+
+## 使い方
+```python
+from transformers import pipeline
+
+text_sim_pipeline = pipeline(
+    model="llm-book/bert-base-japanese-v3-jsts",
+    function_to_apply="none",
+)
+text = "川べりでサーフボードを持った人たちがいます"
+sim_text = "サーファーたちが川べりに立っています"
+# textとsim_textの類似度を計算
+result = text_sim_pipeline({"text": text, "text_pair": sim_text})
+print(result["score"])
+# 3.5703558921813965
+```
+
+## ライセンス
+
+[Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0)

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "results_jsts/bert-base-japanese-v3/lr_2e-05_epochs_3_seed_42",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "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",
+  "problem_type": "regression",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32768
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a4888a7bb3e251b2ff3c0be5f5374b41ea66c593a4afa6212dcebd697f1b728
+size 444901749

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 +1,22 @@
+{
+  "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,
+  "name_or_path": "results_jsts/bert-base-japanese-v3/lr_2e-05_epochs_3_seed_42",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "subword_tokenizer_type": "wordpiece",
+  "sudachi_kwargs": null,
+  "tokenizer_class": "BertJapaneseTokenizer",
+  "unk_token": "[UNK]",
+  "word_tokenizer_type": "mecab"
+}