xsum_108_5000000_2500000_test

This is a BERTopic model. BERTopic is a flexible and modular topic modeling framework that allows for the generation of easily interpretable topics from large datasets.

Usage

To use this model, please install BERTopic:

pip install -U bertopic

You can use the model as follows:

from bertopic import BERTopic
topic_model = BERTopic.load("KingKazma/xsum_108_5000000_2500000_test")

topic_model.get_topic_info()

Topic overview

Number of topics: 14
Number of training documents: 11334

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	said - win - first - one - time	13	-1_said_win_first_one
0	said - mr - would - people - also	1003	0_said_mr_would_people
1	win - game - league - goal - right	7868	1_win_game_league_goal
2	race - olympic - sport - gold - team	1707	2_race_olympic_sport_gold
3	england - cricket - wicket - test - captain	225	3_england_cricket_wicket_test
4	race - hamilton - mercedes - f1 - lap	192	4_race_hamilton_mercedes_f1
5	match - murray - konta - seed - set	62	5_match_murray_konta_seed
6	round - birdie - shot - par - bogey	59	6_round_birdie_shot_par
7	fight - boxing - champion - ali - title	49	7_fight_boxing_champion_ali
8	yn - ar - ei - yr - wedi	48	8_yn_ar_ei_yr
9	unsupported - updated - playback - media - device	33	9_unsupported_updated_playback_media
10	world - champion - osullivan - event - snooker	29	10_world_champion_osullivan_event
11	fifa - blatter - football - platini - fifas	25	11_fifa_blatter_football_platini
12	ebola - sierra - leone - outbreak - people	21	12_ebola_sierra_leone_outbreak

Training hyperparameters

calculate_probabilities: True
language: english
low_memory: False
min_topic_size: 10
n_gram_range: (1, 1)
nr_topics: None
seed_topic_list: None
top_n_words: 10
verbose: False

Framework versions

Numpy: 1.22.4
HDBSCAN: 0.8.33
UMAP: 0.5.3
Pandas: 1.5.3
Scikit-Learn: 1.2.2
Sentence-transformers: 2.2.2
Transformers: 4.31.0
Numba: 0.57.1
Plotly: 5.13.1
Python: 3.10.12