Add files

.markdownlint.json

@@ -0,0 +1,7 @@
+{
+    "MD007": {
+        "indent": 4
+    },
+    "line-length": false,
+    "no-inline-html": false
+}

README.md

@@ -0,0 +1,23 @@
+---
+language: ja
+tags:
+- t5
+- text2text-generation
+- text-classification
+license: apache-2.0
+---
+
+# Pilota model for scud2query
+
+A model for [Pilota](https://github.com/megagonlabs/pilota) trained with <https://github.com/megagonlabs/scud2query>.
+
+- ``scud``
+    - Fine tuned model of [t5-base-japanese-web (with Byte-fallback, 8K)](https://huggingface.co/megagonlabs/t5-base-japanese-web-8k)
+    - The original model is distributed in [the Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0)
+- ``scorer``
+    - Fine tuned model of [LINE DistilBERT Japanese](https://huggingface.co/line-corporation/line-distilbert-base-japanese)
+    - The original model is distributed in [the Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0)
+
+## License
+
+Apache License 2.0

scorer/config.json

@@ -0,0 +1,48 @@
+{
+    "_name_or_path": "line-corporation/line-distilbert-base-japanese",
+    "activation": "gelu",
+    "architectures": [
+        "DistilBertForSequenceClassification"
+    ],
+    "attention_dropout": 0.1,
+    "dim": 768,
+    "dropout": 0.1,
+    "hidden_dim": 3072,
+    "id2label": {
+        "0": "OK",
+        "1": "incorrect_none",
+        "2": "lack",
+        "3": "limited",
+        "4": "untruth"
+    },
+    "initializer_range": 0.02,
+    "label2id": {
+        "OK": 0,
+        "incorrect_none": 1,
+        "lack": 2,
+        "limited": 3,
+        "untruth": 4
+    },
+    "max_position_embeddings": 512,
+    "model_type": "distilbert",
+    "n_heads": 12,
+    "n_layers": 6,
+    "output_hidden_states": true,
+    "pad_token_id": 0,
+    "problem_type": "multi_label_classification",
+    "qa_dropout": 0.1,
+    "seq_classif_dropout": 0.2,
+    "sinusoidal_pos_embds": true,
+    "tie_weights_": true,
+    "torch_dtype": "float32",
+    "transformers_version": "4.30.2",
+    "vocab_size": 32768,
+    "my_labels": [
+        "OK",
+        "incorrect_none",
+        "lack",
+        "limited",
+        "untruth"
+    ],
+    "singlebinary": false
+}

scorer/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cd6935e641b8e8b2dddeda7dfd44356540e6b1d1bbbf6d56ba9df08c5dbe41b
+size 274764461

scorer/scorer.config.json

@@ -0,0 +1,3 @@
+{
+    "context_separator": "<context>"
+}

scorer/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "unk_token": "<unk>"
+}

scorer/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfafc8c0662d9c8f39621a64c74260f2ad120310c8dd24886de2dddaf599b4e
+size 439391

scorer/tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "auto_map": {
+    "AutoTokenizer": [
+      "line-corporation/line-distilbert-base-japanese--distilbert_japanese_tokenizer.DistilBertJapaneseTokenizer",
+      null
+    ]
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "do_subword_tokenize": true,
+  "do_word_tokenize": true,
+  "eos_token": "[SEP]",
+  "is_fast": true,
+  "jumanpp_kwargs": null,
+  "keep_accents": true,
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mecab_kwargs": {
+    "mecab_dic": "unidic_lite"
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "subword_tokenizer_type": "sentencepiece",
+  "sudachi_kwargs": null,
+  "tokenize_chinese_chars": false,
+  "tokenizer_class": "DistilBertJapaneseTokenizer",
+  "unk_token": "<unk>",
+  "word_tokenizer_type": "mecab"
+}

scud/added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "</target>": 8101,
+  "<agent>": 8103,
+  "<context>": 8102,
+  "<target>": 8100,
+  "<user>": 8104
+}

scud/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "megagonlabs/t5-base-japanese-web-8k",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "gradient_checkpointing": false,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "use_cache": true,
+  "vocab_size": 8105
+}

scud/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.30.2"
+}

scud/pilota.config.json

@@ -0,0 +1,6 @@
+{
+    "size_context": 0,
+    "acceptable_names": [
+        "user"
+    ]
+}

scud/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c580562efd602dfdcf2431a0db1a9006a6aeda1816b0f8b0a9c280d22d3f85df
+size 842811573

scud/special_tokens_map.json

@@ -0,0 +1,107 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

scud/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44349399ce87d5409b3ca15780d27ada474dc74ff2a112b08402605444e61a2a
+size 350029

scud/tokenizer_config.json

@@ -0,0 +1,113 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>",
+  "use_fast": false
+}