transformers_issues_topics

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("noumanjavaid/transformers_issues_topics")

topic_model.get_topic_info()

Topic overview

• Number of topics: 30
• Number of training documents: 9000

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	models - bert - model - tensorflow - tokenizers	14	-1_models_bert_model_tensorflow
0	tokenizer - tokenizers - tokenization - token - tokens	2078	0_tokenizer_tokenizers_tokenization_token
1	pytorch - tensorflow - modelingutilspy - attributeerror - runtimeerror	1886	1_pytorch_tensorflow_modelingutilspy_attributeerror
2	trainertrain - trainer - trainers - training - evaluateduringtraining	696	2_trainertrain_trainer_trainers_training
3	summarization - summaries - summary - examples - sentencepiece	636	3_summarization_summaries_summary_examples
4	gpt2tokenizer - gpt2 - gpt2tokenizerfast - gpt2model - gpt	452	4_gpt2tokenizer_gpt2_gpt2tokenizerfast_gpt2model
5	modelcard - modelcards - card - model - models	451	5_modelcard_modelcards_card_model
6	typos - typo - fix - correction - fixed	446	6_typos_typo_fix_correction
7	readmemd - readmetxt - readme - modelcard - file	284	7_readmemd_readmetxt_readme_modelcard
8	t5 - t5model - t5base - tf - t5large	256	8_t5_t5model_t5base_tf
9	longformer - longformers - longformerformultiplechoice - longformertokenizerfast - attentions	254	9_longformer_longformers_longformerformultiplechoice_longformertokenizerfast
10	seq2seq - seq2seqtrainer - seq2seqdataset - seq2seqfinetunepy - runseq2seq	223	10_seq2seq_seq2seqtrainer_seq2seqdataset_seq2seqfinetunepy
11	pipeline - pipelines - ner - pipelinesentimentanalysis - nerpipeline	209	11_pipeline_pipelines_ner_pipelinesentimentanalysis
12	ci - testing - tests - test - testgeneratefp16	175	12_ci_testing_tests_test
13	deprecate - deprecation - deprecated - warnings - warning	136	13_deprecate_deprecation_deprecated_warnings
14	onnxonnxruntime - onnx - 04onnxexport - 04onnxexportipynb - benchmarkonnxexport	129	14_onnxonnxruntime_onnx_04onnxexport_04onnxexportipynb
15	datacollatorforlanguagemodelingfile - datacollatorforlanguagemodeling - datacollatorforlanguagemodelling - datacollatorforpermutationlanguagemodeling - labelsmoothingfactor	100	15_datacollatorforlanguagemodelingfile_datacollatorforlanguagemodeling_datacollatorforlanguagemodelling_datacollatorforpermutationlanguagemodeling
16	deberta - debertav2 - debertav2initpy - debertatokenizer - debertav2xxlargemnli	73	16_deberta_debertav2_debertav2initpy_debertatokenizer
17	benchmark - benchmarking - benchmarks - comparison - results	63	17_benchmark_benchmarking_benchmarks_comparison
18	generationbeamsearchpy - generatebeamsearch - generatebeamsearchoutputs - beamsearch - nonbeamsearch	61	18_generationbeamsearchpy_generatebeamsearch_generatebeamsearchoutputs_beamsearch
19	wandbproject - wandb - wandbcallback - wandbdisabled - wandbdisabledtrue	56	19_wandbproject_wandb_wandbcallback_wandbdisabled
20	wav2vec2 - wav2vec - wav2vec20 - wav2vec2forctc - wav2vec2xlrswav2vec2	54	20_wav2vec2_wav2vec_wav2vec20_wav2vec2forctc
21	flax - flaxelectraformaskedlm - flaxelectraforpretraining - flaxjax - flaxelectramodel	49	21_flax_flaxelectraformaskedlm_flaxelectraforpretraining_flaxjax
22	configpath - configs - config - configuration - modelconfigs	49	22_configpath_configs_config_configuration
23	logging - logs - log - logger - loggingfirststep	45	23_logging_logs_log_logger
24	cachedir - cache - cachedpath - caching - cached	34	24_cachedir_cache_cachedpath_caching
25	electra - electrapretrainedmodel - electraformaskedlm - electraformultiplechoice - electrafortokenclassification	34	25_electra_electrapretrainedmodel_electraformaskedlm_electraformultiplechoice
26	layoutlm - layoutlmtokenizer - layout - layoutlmbaseuncased - tf	23	26_layoutlm_layoutlmtokenizer_layout_layoutlmbaseuncased
27	dict - dictstr - returndict - parse - arguments	17	27_dict_dictstr_returndict_parse
28	pplm - pr - deprecated - variable - ppl	17	28_pplm_pr_deprecated_variable

Training hyperparameters

• calculate_probabilities: False
• language: english
• low_memory: False
• min_topic_size: 10
• n_gram_range: (1, 1)
• nr_topics: 30
• 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: 0.8.37
• UMAP: 0.5.6
• Pandas: 2.0.3
• Scikit-Learn: 1.2.2
• Sentence-transformers: 3.0.1
• Transformers: 4.41.2
• Numba: 0.58.1
• Plotly: 5.15.0
• Python: 3.10.12