abir-hr196/clt_gpt2_nonenglish_tokenized2

--- dataset_info: features: - name: input_ids sequence: int32 splits: - name: deu_Latn num_bytes: 240894732 num_examples: 223613 - name: arb_Arab num_bytes: 241456408 num_examples: 364006 - name: cmn_Hani num_bytes: 241169928 num_examples: 292415 - name: fra_Latn num_bytes: 240332112 num_examples: 83004 download_size: 1515068815 dataset_size: 963853180 configs: - config_name: default data_files: - split: deu_Latn path: data/deu_Latn-* - split: arb_Arab path: data/arb_Arab-* - split: cmn_Hani path: data/cmn_Hani-* - split: fra_Latn path: data/fra_Latn-* ---dataset_info: features: - name: input_ids sequence: int32 splits: - name: deu_Latn（德语-拉丁字母） num_bytes: 240894732 num_examples: 223613 - name: arb_Arab（阿拉伯语-阿拉伯字母） num_bytes: 241456408 num_examples: 364006 - name: cmn_Hani（中文-汉字） num_bytes: 241169928 num_examples: 292415 - name: fra_Latn（法语-拉丁字母） num_bytes: 240332112 num_examples: 83004 download_size: 1515068815 dataset_size: 963853180 configs: - config_name: default data_files: - split: deu_Latn path: data/deu_Latn-* - split: arb_Arab path: data/arb_Arab-* - split: cmn_Hani path: data/cmn_Hani-* - split: fra_Latn path: data/fra_Latn-*