diff --git "a/tokenizer.json" "b/tokenizer.json" new file mode 100644--- /dev/null +++ "b/tokenizer.json" @@ -0,0 +1,512202 @@ +{ + "version": "1.0", + "truncation": { + "direction": "Right", + "max_length": 1024, + "strategy": "LongestFirst", + "stride": 0 + }, + "padding": { + "strategy": "BatchLongest", + "direction": "Right", + "pad_to_multiple_of": null, + "pad_id": 0, + "pad_type_id": 0, + "pad_token": "[PAD]" + }, + "added_tokens": [ + { + "id": 0, + "content": "[PAD]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 1, + "content": "[CLS]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2, + "content": "[SEP]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 3, + "content": "[UNK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": true + }, + { + "id": 128000, + "content": "[MASK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 128001, + "content": "<