| log_interval: 100000 | |
| top_k: 10 | |
| batch_size: 4096 | |
| query_preprocess_pipeline: | |
| processor_type: [] | |
| length_filter_config: | |
| max_tokens: null | |
| min_tokens: null | |
| max_chars: null | |
| min_chars: null | |
| max_bytes: null | |
| min_bytes: null | |
| tokenizer_config: | |
| tokenizer_type: moses | |
| hf_tokenizer_path: null | |
| tiktok_tokenizer_name: null | |
| lang: null | |
| token_normalize_config: | |
| lang: en | |
| penn: true | |
| norm_quote_commas: true | |
| norm_numbers: true | |
| pre_replace_unicode_punct: false | |
| post_remove_control_chars: false | |
| perl_parity: false | |
| truncate_config: | |
| max_chars: null | |
| max_bytes: null | |
| max_tokens: null | |
| tokenizer_config: | |
| tokenizer_type: moses | |
| hf_tokenizer_path: null | |
| tiktok_tokenizer_name: null | |
| lang: null | |
| retriever_path: null | |
| indexes_merge_method: linear | |
| used_indexes: null | |