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("davanstrien/transformers_issues_topics")

topic_model.get_topic_info()

Topic overview

• Number of topics: 30
• Number of training documents: 7235

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	encoder - bert - tensorflow - decoder - output	11	-1_encoder_bert_tensorflow_decoder
0	tokenizer - tokenizers - tokenization - tokenize - berttokenizer	2265	0_tokenizer_tokenizers_tokenization_tokenize
1	cuda - runtimeerror - conda - pytorch - tensorflow	1513	1_cuda_runtimeerror_conda_pytorch
2	readmemd - readmetxt - readme - docstring - docstrings	763	2_readmemd_readmetxt_readme_docstring
3	trainertrain - trainer - trainertfpy - trainers - training	550	3_trainertrain_trainer_trainertfpy_trainers
4	rag - roberta - robertatokenizer - robertatokenizerfast - robertabase	546	4_rag_roberta_robertatokenizer_robertatokenizerfast
5	modelcard - modelcards - card - model - cards	473	5_modelcard_modelcards_card_model
6	importerror - transformerscli - transformers - transformerxl - transformer	432	6_importerror_transformerscli_transformers_transformerxl
7	seq2seq - seq2seqtrainer - seq2seqdataset - runseq2seq - examplesseq2seq	405	7_seq2seq_seq2seqtrainer_seq2seqdataset_runseq2seq
8	gpt2 - gpt2tokenizer - gpt2xl - gpt2tokenizerfast - gpt	365	8_gpt2_gpt2tokenizer_gpt2xl_gpt2tokenizerfast
9	t5 - t5model - t5base - t5large - tf	289	9_t5_t5model_t5base_t5large
10	tests - testing - speedup - test - testgeneratefp16	230	10_tests_testing_speedup_test
11	questionansweringpipeline - questionanswering - answering - questionasnwering - distilbertforquestionanswering	138	11_questionansweringpipeline_questionanswering_answering_questionasnwering
12	ner - pipeline - pipelinener - pipelines - pipelineframework	138	12_ner_pipeline_pipelinener_pipelines
13	deberta - debertav2 - debertav2initpy - debertatokenizer - distilbertmodel	132	13_deberta_debertav2_debertav2initpy_debertatokenizer
14	onnxonnxruntime - onnx - onnxexport - 04onnxexport - 04onnxexportipynb	110	14_onnxonnxruntime_onnx_onnxexport_04onnxexport
15	benchmark - benchmarks - accuracy - precision - comparison	85	15_benchmark_benchmarks_accuracy_precision
16	labelsmoothingfactor - labelsmoothednllloss - labelsmoothing - labels - label	79	16_labelsmoothingfactor_labelsmoothednllloss_labelsmoothing_labels
17	longformer - longformers - longform - longformerforqa - longformerlayer	71	17_longformer_longformers_longform_longformerforqa
18	generationbeamsearchpy - generatebeamsearch - beamsearch - nonbeamsearch - beam	60	18_generationbeamsearchpy_generatebeamsearch_beamsearch_nonbeamsearch
19	cachedir - cache - cachedpath - caching - cached	58	19_cachedir_cache_cachedpath_caching
20	wav2vec2 - wav2vec - wav2vec20 - wav2vec2forctc - wav2vec2xlrswav2vec2	56	20_wav2vec2_wav2vec_wav2vec20_wav2vec2forctc
21	flax - flaxelectraformaskedlm - flaxelectraforpretraining - flaxjax - flaxelectramodel	52	21_flax_flaxelectraformaskedlm_flaxelectraforpretraining_flaxjax
22	wandbproject - wandb - wandbcallback - wandbdisabled - wandbdisabledtrue	49	22_wandbproject_wandb_wandbcallback_wandbdisabled
23	electra - electrapretrainedmodel - electraformaskedlm - electraformultiplechoice - electrafortokenclassification	38	23_electra_electrapretrainedmodel_electraformaskedlm_electraformultiplechoice
24	layoutlm - layout - layoutlmtokenizer - layoutlmbaseuncased - tf	24	24_layoutlm_layout_layoutlmtokenizer_layoutlmbaseuncased
25	notebook - notebooks - community - text - multilabel	18	25_notebook_notebooks_community_text
26	dict - dictstr - returndict - parse - arguments	18	26_dict_dictstr_returndict_parse
27	pplm - pr - deprecated - variable - ppl	17	27_pplm_pr_deprecated_variable
28	isort - github - repo - version - setupcfg	15	28_isort_github_repo_version

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

Framework versions

• Numpy: 1.22.4
• HDBSCAN: 0.8.29
• UMAP: 0.5.3
• Pandas: 1.5.3
• Scikit-Learn: 1.2.2
• Sentence-transformers: 2.2.2
• Transformers: 4.29.2
• Numba: 0.56.4
• Plotly: 5.13.1
• Python: 3.10.11