open-mar11Top10

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("Thang203/open-mar11Top10")

topic_model.get_topic_info()

Topic overview

• Number of topics: 10
• Number of training documents: 2109

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	models - language - model - language models - llms	11	-1_models_language_model_language models
0	models - language - model - llms - language models	597	0_models_language_model_llms
1	models - quantization - language - training - model	1001	1_models_quantization_language_training
2	models - attacks - llms - language - text	222	2_models_attacks_llms_language
3	bias - biases - gender - models - language	164	3_bias_biases_gender_models
4	music - poetry - generation - poems - model	45	4_music_poetry_generation_poems
5	hallucinations - hallucination - models - large - language models	23	5_hallucinations_hallucination_models_large
6	claim - legal - claims - generation - based	20	6_claim_legal_claims_generation
7	financial - analysis - chinese - financial domain - language	14	7_financial_analysis_chinese_financial domain
8	summarization - summaries - abstractive - abstractive summarization - summary	12	8_summarization_summaries_abstractive_abstractive summarization

Training hyperparameters

• calculate_probabilities: False
• language: english
• low_memory: False
• min_topic_size: 10
• n_gram_range: (1, 1)
• nr_topics: 10
• seed_topic_list: None
• top_n_words: 10
• verbose: True
• zeroshot_min_similarity: 0.7
• zeroshot_topic_list: None

Framework versions

• Numpy: 1.25.2
• HDBSCAN: 0.8.33
• UMAP: 0.5.5
• Pandas: 1.5.3
• Scikit-Learn: 1.2.2
• Sentence-transformers: 2.6.1
• Transformers: 4.38.2
• Numba: 0.58.1
• Plotly: 5.15.0
• Python: 3.10.12