Upload tokenizer

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+ "bos_token": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "cls_token": {
+ "content": "<CLS|LLM-jp>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "mask_token": {
+ "content": "<MASK|LLM-jp>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<PAD|LLM-jp>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "sep_token": {
+ "content": "<SEP|LLM-jp>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "unk_token": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}

tokenizer_config.json

@@ -0,0 +1,84 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "added_tokens_decoder": {
+ "0": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "3": {
+ "content": "<MASK|LLM-jp>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "4": {
+ "content": "<PAD|LLM-jp>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "5": {
+ "content": "<CLS|LLM-jp>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "6": {
+ "content": "<SEP|LLM-jp>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "7": {
+ "content": "<EOD|LLM-jp>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "<s>",
+ "chat_template": "{{bos_token}}{% for message in messages %}{% if message['role'] == 'user' %}{{ '\\n\\n### 指示:\\n' + message['content'] }}{% elif message['role'] == 'system' %}{{ '以下は、タスクを説明する指示です。要求を適切に満たす応答を書きなさい。' }}{% elif message['role'] == 'assistant' %}{{ '\\n\\n### 応答:\\n' + message['content'] + eos_token }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '\\n\\n### 応答:\\n' }}{% endif %}{% endfor %}",
+ "clean_up_tokenization_spaces": false,
+ "cls_token": "<CLS|LLM-jp>",
+ "eod_token": "</s>",
+ "eos_token": "</s>",
+ "extra_ids": 0,
+ "mask_token": "<MASK|LLM-jp>",
+ "model_max_length": 2048,
+ "pad_token": "<PAD|LLM-jp>",
+ "sep_token": "<SEP|LLM-jp>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "PreTrainedTokenizerFast",
+ "unk_token": "<unk>"
+}