TheFinAI/ins_filtered

---
dataset_info:
features:
- name: id
dtype: string
- name: source
dtype: string
- name: type
dtype: string
- name: subject
dtype: string
- name: instruction
dtype: string
- name: response
dtype: string
- name: needs_filter
dtype: bool
- name: src_type
dtype: string
- name: year
dtype: string
splits:
- name: year_backbone
num_bytes: 10925019
num_examples: 20000
- name: year_2001
num_bytes: 10967660
num_examples: 20000
- name: year_2002
num_bytes: 11015270
num_examples: 20000
- name: year_2003
num_bytes: 10956520
num_examples: 20000
- name: year_2004
num_bytes: 11033552
num_examples: 20000
- name: year_2005
num_bytes: 10911407
num_examples: 20000
- name: year_2006
num_bytes: 11037283
num_examples: 20000
- name: year_2007
num_bytes: 11000531
num_examples: 20000
- name: year_2008
num_bytes: 11039282
num_examples: 20000
- name: year_2009
num_bytes: 11059995
num_examples: 20000
- name: year_2010
num_bytes: 10932522
num_examples: 20000
- name: year_2011
num_bytes: 10980909
num_examples: 20000
- name: year_2012
num_bytes: 10919999
num_examples: 20000
- name: year_2013
num_bytes: 11076239
num_examples: 20000
- name: year_2014
num_bytes: 10902245
num_examples: 20000
- name: year_2015
num_bytes: 10979918
num_examples: 20000
- name: year_2016
num_bytes: 10869139
num_examples: 20000
- name: year_2017
num_bytes: 10987279
num_examples: 20000
- name: year_2018
num_bytes: 11007874
num_examples: 20000
- name: year_2019
num_bytes: 10995509
num_examples: 20000
- name: year_2020
num_bytes: 10981568
num_examples: 20000
- name: year_2021
num_bytes: 10979889
num_examples: 20000
- name: year_2022
num_bytes: 10991480
num_examples: 20000
- name: year_2023
num_bytes: 10898584
num_examples: 20000
- name: year_2024
num_bytes: 11062331
num_examples: 20000
- name: year_2025
num_bytes: 10907291
num_examples: 20000
download_size: 285419295
dataset_size: 285419295
configs:
- config_name: default
data_files:
- split: year_backbone
path: data/year_backbone.parquet
- split: year_2001
path: data/year_2001.parquet
- split: year_2002
path: data/year_2002.parquet
- split: year_2003
path: data/year_2003.parquet
- split: year_2004
path: data/year_2004.parquet
- split: year_2005
path: data/year_2005.parquet
- split: year_2006
path: data/year_2006.parquet
- split: year_2007
path: data/year_2007.parquet
- split: year_2008
path: data/year_2008.parquet
- split: year_2009
path: data/year_2009.parquet
- split: year_2010
path: data/year_2010.parquet
- split: year_2011
path: data/year_2011.parquet
- split: year_2012
path: data/year_2012.parquet
- split: year_2013
path: data/year_2013.parquet
- split: year_2014
path: data/year_2014.parquet
- split: year_2015
path: data/year_2015.parquet
- split: year_2016
path: data/year_2016.parquet
- split: year_2017
path: data/year_2017.parquet
- split: year_2018
path: data/year_2018.parquet
- split: year_2019
path: data/year_2019.parquet
- split: year_2020
path: data/year_2020.parquet
- split: year_2021
path: data/year_2021.parquet
- split: year_2022
path: data/year_2022.parquet
- split: year_2023
path: data/year_2023.parquet
- split: year_2024
path: data/year_2024.parquet
- split: year_2025
path: data/year_2025.parquet
---