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("flumboyantApple/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	bert - pytorch - tensorflow - pretrained - gpu	12	-1_bert_pytorch_tensorflow_pretrained
0	tokenizer - tokenizers - tokenization - tokenize - encoderdecoder	2279	0_tokenizer_tokenizers_tokenization_tokenize
1	cuda - pytorch - tensorflow - gpu - gpus	1830	1_cuda_pytorch_tensorflow_gpu
2	modelcard - modelcards - card - model - cards	887	2_modelcard_modelcards_card_model
3	seq2seq - s2s - seq2seqtrainer - seq2seqdataset - runseq2seq	451	3_seq2seq_s2s_seq2seqtrainer_seq2seqdataset
4	trainer - trainertrain - trainers - training - evaluateduringtraining	445	4_trainer_trainertrain_trainers_training
5	albertbasev2 - albertforpretraining - albert - albertformaskedlm - albertmodel	435	5_albertbasev2_albertforpretraining_albert_albertformaskedlm
6	gpt2 - gpt2tokenizer - gpt2xl - gpt2tokenizerfast - gpt	347	6_gpt2_gpt2tokenizer_gpt2xl_gpt2tokenizerfast
7	typos - typo - fix - correction - fixed	278	7_typos_typo_fix_correction
8	readmemd - readmetxt - readme - file - camembertbasereadmemd	274	8_readmemd_readmetxt_readme_file
9	t5 - t5model - tf - t5base - t5large	259	9_t5_t5model_tf_t5base
10	transformerscli - transformers - transformer - importerror - import	228	10_transformerscli_transformers_transformer_importerror
11	ci - testing - tests - testgeneratefp16 - test	198	11_ci_testing_tests_testgeneratefp16
12	longformerforquestionanswering - questionansweringpipeline - tfalbertforquestionanswering - distilbertforquestionanswering - questionanswering	142	12_longformerforquestionanswering_questionansweringpipeline_tfalbertforquestionanswering_distilbertforquestionanswering
13	pipeline - pipelines - ner - fixpipeline - nerpipeline	140	13_pipeline_pipelines_ner_fixpipeline
14	longformer - longformers - longform - longformerlayer - longformermodel	136	14_longformer_longformers_longform_longformerlayer
15	benchmark - benchmarks - accuracy - precision - hardcoded	113	15_benchmark_benchmarks_accuracy_precision
16	onnx - onnxexport - onnxonnxruntime - onnxruntime - 04onnxexport	77	16_onnx_onnxexport_onnxonnxruntime_onnxruntime
17	generationbeamsearchpy - generatebeamsearch - beamsearch - nonbeamsearch - beam	76	17_generationbeamsearchpy_generatebeamsearch_beamsearch_nonbeamsearch
18	flax - flaxelectraformaskedlm - flaxelectraforpretraining - flaxjax - flaxelectramodel	75	18_flax_flaxelectraformaskedlm_flaxelectraforpretraining_flaxjax
19	datacollatorforlanguagemodelingfile - datacollatorforlanguagemodeling - datacollatorforlanguagemodelling - datacollatorforpermutationlanguagemodeling - runlanguagemodelingpy	49	19_datacollatorforlanguagemodelingfile_datacollatorforlanguagemodeling_datacollatorforlanguagemodelling_datacollatorforpermutationlanguagemodeling
20	huggingfacetokenizers297 - huggingfacetransformers - huggingface - huggingfaces - huggingfacecn	43	20_huggingfacetokenizers297_huggingfacetransformers_huggingface_huggingfaces
21	cachedir - cache - cachedpath - caching - cached	43	21_cachedir_cache_cachedpath_caching
22	notebook - notebooks - blenderbot3b - community - blenderbot	35	22_notebook_notebooks_blenderbot3b_community
23	wandbproject - ga - wandbcallback - wandb - fork	33	23_wandbproject_ga_wandbcallback_wandb
24	closed - adding - add - bort - added	32	24_closed_adding_add_bort
25	electra - electrapretrainedmodel - electraformaskedlm - electralarge - electraformultiplechoice	27	25_electra_electrapretrainedmodel_electraformaskedlm_electralarge
26	layoutlm - layout - layoutlmtokenizer - layoutlmbaseuncased - tf	23	26_layoutlm_layout_layoutlmtokenizer_layoutlmbaseuncased
27	pplm - pr - deprecated - variable - ppl	18	27_pplm_pr_deprecated_variable
28	isort - blackisortflake8 - github - repo - version	15	28_isort_blackisortflake8_github_repo

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: 1.23.3
• HDBSCAN: 0.8.38.post1
• UMAP: 0.5.6
• Pandas: 1.5.3
• Scikit-Learn: 1.1.2
• Sentence-transformers: 3.0.1
• Transformers: 4.44.1
• Numba: 0.60.0
• Plotly: 5.10.0
• Python: 3.9.18