Add CLIP text encoder for Japanese

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "sonoisa/clip-base-japanese",
+  "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",
+  "tokenizer_class": "BertJapaneseTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.14.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

output_linear.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9f70fed6ae69babf7903af298d9895f9769e00a00db96b1bd59c7ab764b84c8
+size 4721639

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9c467fa7d9e8dd2dfdbc19ba42889e66cfded819ee69a259ad46c6a990d26ce
+size 442547953

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "do_lower_case": true, "do_word_tokenize": true, "do_subword_tokenize": true, "word_tokenizer_type": "mecab", "subword_tokenizer_type": "wordpiece", "never_split": null, "mecab_kwargs": null, "is_fast": true, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "sonoisa/clip-base-japanese", "tokenizer_class": "BertJapaneseTokenizer"}

training_args.json

@@ -0,0 +1,20 @@
+{
+    "adam_epsilon": 1e-08,
+    "data_dir": "/content/data",
+    "early_stop_callback": false,
+    "eval_batch_size": 8,
+    "fp_16": false,
+    "gradient_accumulation_steps": 4,
+    "learning_rate": 0.001,
+    "max_grad_norm": 1.0,
+    "max_input_length": 64,
+    "model_name_or_path": "cl-tohoku/bert-base-japanese-whole-word-masking",
+    "n_gpu": 1,
+    "num_train_epochs": 2,
+    "seed": 42,
+    "shuffle_buffer_size": 65536,
+    "tokenizer_name_or_path": "cl-tohoku/bert-base-japanese-whole-word-masking",
+    "train_batch_size": 256,
+    "warmup_ratio": 0.05,
+    "weight_decay": 0.0
+}