AISE-TUDelft/babel_el22222

--- dataset_info: features: - name: Column1 dtype: string - name: content dtype: string - name: repo dtype: string - name: path dtype: string - name: token_length dtype: int64 - name: original_comment dtype: string - name: comment_type dtype: string - name: detected_lang dtype: string - name: prompt dtype: string - name: file-tokens-Qwen/CodeQwen1.5-7B dtype: int64 - name: comment-tokens-Qwen/CodeQwen1.5-7B dtype: int64 - name: comment_tail_length_Qwen/CodeQwen1.5-7B dtype: int64 - name: file-tokens-bigcode/starcoder2-7b dtype: int64 - name: comment-tokens-bigcode/starcoder2-7b dtype: int64 - name: comment_tail_length_bigcode/starcoder2-7b dtype: int64 - name: file-tokens-google/codegemma-7b dtype: int64 - name: comment-tokens-google/codegemma-7b dtype: int64 - name: comment_tail_length_google/codegemma-7b dtype: int64 - name: file-tokens-ibm-granite/granite-8b-code-base dtype: int64 - name: comment-tokens-ibm-granite/granite-8b-code-base dtype: int64 - name: comment_tail_length_ibm-granite/granite-8b-code-base dtype: int64 - name: file-tokens-meta-llama/CodeLlama-7b-hf dtype: int64 - name: comment-tokens-meta-llama/CodeLlama-7b-hf dtype: int64 - name: comment_tail_length_meta-llama/CodeLlama-7b-hf dtype: int64 - name: excluded-based-on-tokenizer-Qwen/CodeQwen1.5-7B dtype: bool - name: excluded-based-on-tokenizer-bigcode/starcoder2-7b dtype: bool - name: excluded-based-on-tokenizer-google/codegemma-7b dtype: bool - name: excluded-based-on-tokenizer-ibm-granite/granite-8b-code-base dtype: bool - name: excluded-based-on-tokenizer-meta-llama/CodeLlama-7b-hf dtype: bool - name: include-for-inference dtype: bool splits: - name: train num_bytes: 865232 num_examples: 91 download_size: 364199 dataset_size: 865232 configs: - config_name: default data_files: - split: train path: data/train-* ---