-
Notifications
You must be signed in to change notification settings - Fork 178
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
* release dj v0.2.0 (dj_video) * authored by data-juicer team
- Loading branch information
Showing
172 changed files
with
11,515 additions
and
1,040 deletions.
There are no files selected for viewing
Large diffs are not rendered by default.
Oops, something went wrong.
Large diffs are not rendered by default.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,60 @@ | ||
| project_name: 'llava-1.5-pretrain-dataset-refine-recipe' | ||
| dataset_path: 'blip_laion_cc_sbu_558k_dj_fmt_only_caption.jsonl' # converted LLaVA pretrain dataset in Data-Juicer format with only_keep_caption is True. See tools/multimodal/source_format_to_data_juicer_format/llava_to_dj.py | ||
| export_path: 'blip_laion_cc_sbu_558k_dj_fmt_only_caption_refined.jsonl' | ||
|
|
||
| np: 42 # number of subprocess to process your dataset | ||
| text_keys: 'text' # the key name of field where the sample texts to be processed, e.g., `text`, `instruction`, `output`, ... | ||
|
|
||
| # for multimodal data processing | ||
| image_key: 'images' # Key name of field to store the list of sample image paths. | ||
| image_special_token: '<image>' # The special token that represents an image in the text. For LLaVA, it's "<image>". Should be aligned with the args when running conversion tools. | ||
| eoc_special_token: '<|__dj__eoc|>' # The special token that represents the end of a chunk in the text. In default, it's "<|__dj__eoc|>". You can specify your own special token according to your input dataset. Should be aligned with the args when running conversion tools. | ||
|
|
||
| open_tracer: true | ||
|
|
||
| # process schedule: a list of several process operators with their arguments | ||
| process: | ||
| - fix_unicode_mapper: # fix unicode errors in text. | ||
| - punctuation_normalization_mapper: # normalize unicode punctuations to English punctuations. | ||
|
|
||
| # 558128 | ||
| # Filter ops | ||
| - alphanumeric_filter: #558087 # filter text with alphabet/numeric ratio out of specific range. | ||
| tokenization: false # Whether to count the ratio of alphanumeric to the total number of tokens. | ||
| min_ratio: 0.60 # the min ratio of filter range | ||
| - character_repetition_filter: #546105 # filter text with the character repetition ratio out of specific range | ||
| rep_len: 10 # repetition length for char-level n-gram | ||
| max_ratio: 0.09373663 # the max ratio of filter range | ||
| - flagged_words_filter: #543960 # filter text with the flagged-word ratio larger than a specific max value | ||
| lang: en # consider flagged words in what language | ||
| tokenization: false # whether to use model to tokenize documents | ||
| max_ratio: 0.0 # the max ratio to filter text | ||
| - perplexity_filter: #532029 # filter text with perplexity score out of specific range | ||
| lang: en # compute perplexity in what language | ||
| max_ppl: 14435.5806 # the max perplexity score to filter text | ||
| - special_characters_filter: #531968 # filter text with special-char ratio out of specific range | ||
| min_ratio: 0.16534802 # the min ratio of filter range | ||
| max_ratio: 0.42023757 # the max ratio of filter range | ||
| - word_repetition_filter: # 530773 # filter text with the word repetition ratio out of specific range | ||
| lang: en # sample in which language | ||
| tokenization: false # whether to use model to tokenize documents | ||
| rep_len: 10 # repetition length for word-level n-gram | ||
| max_ratio: 0.03085751 # the max ratio of filter range | ||
|
|
||
| - image_aspect_ratio_filter: #542389 # filter samples according to the aspect ratios of images (a fraction of width by height, r=w/h) in them | ||
| min_ratio: 0.333 # the min aspect ratio of filter range | ||
| max_ratio: 3.0 # the max aspect ratio of filter range | ||
| any_or_all: any # keep this sample when any/all images meet the filter condition | ||
| - image_shape_filter: #533966 # filter samples according to the widths and heights of images in them | ||
| max_width: 727.8798422276 # the max width of width filter range | ||
| max_height: 606.2421072264 # the max height of height filter range | ||
| any_or_all: any # keep this sample when any/all images meet the filter condition | ||
| - image_size_filter: # 533966 # filter samples according to the size of images (in bytes) within them | ||
| max_size: "124KB" # the max size of filter range | ||
| any_or_all: any # keep this sample when any/all images meet the filter condition | ||
| - image_text_similarity_filter: #544202 # filter samples according to the similarity between text and images. | ||
| hf_clip: openai/clip-vit-base-patch32 # name of used Hugging Face clip | ||
| min_score: 0.20315419 # the min similarity of filter range | ||
| - image_text_matching_filter: # filter samples according to the matching score between image and text. | ||
| hf_blip: Salesforce/blip-itm-base-coco # name of used Hugging Face blip | ||
| min_score: 0.44930778 # the min matching score of filter range |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.