Mike Burnham's picture

3 1

Mike Burnham

mlburnham

·

AI & ML interests

None yet

Recent Activity

updated a dataset 8 days ago

mlburnham/polnli_hypothesis_stability

published a dataset 8 days ago

mlburnham/polnli_hypothesis_stability

updated a collection 14 days ago

Political DEBATE

View all activity

Organizations

None yet

mlburnham's activity

updated a dataset 8 days ago

mlburnham/polnli_hypothesis_stability

Viewer • Updated 8 days ago • 8.98k • 24

published a dataset 8 days ago

mlburnham/polnli_hypothesis_stability

Viewer • Updated 8 days ago • 8.98k • 24

updated a collection 14 days ago

Political DEBATE

Zero-shot classifiers for political text. • 4 items • Updated 14 days ago

updated a model 15 days ago

mlburnham/Political_DEBATE_DeBERTa_large_v1.1

Text Classification • Updated 15 days ago • 72

New activity in answerdotai/ModernBERT-base 17 days ago

Speed Benchmarks with MPS Backend

#47 opened 17 days ago by

updated 3 models 17 days ago

mlburnham/Political_DEBATE_ModernBERT_large_v1.0

Text Classification • Updated 17 days ago • 99

mlburnham/Political_DEBATE_DeBERTa_base_v1.1

Text Classification • Updated 17 days ago • 85

mlburnham/Political_DEBATE_ModernBERT_base_v1.0

Text Classification • Updated 17 days ago • 85

updated a collection 18 days ago

Political DEBATE

Zero-shot classifiers for political text. • 4 items • Updated 14 days ago

replied to MoritzLaurer's post 24 days ago

Any plans to train a version of your zero-shot models on ModernBERT? I'm finding that ModernBERT is a huge boost in speed, and a slight drop in performance vs. DeBERTa when I tune it. Not sure if the performance drop is because your zero-shot models were such a strong foundation for transfer learning, or the strength of DeBERTa architecture on NLI.

reacted to MoritzLaurer's post with 👍 about 1 month ago

Post

2605

Quite excited by the ModernBERT release! 0.15/0.4B small, 2T modern pre-training data and tokenizer with code, 8k context window, great efficient model for embeddings & classification!

This will probably be the basis for many future SOTA encoders! And I can finally stop using DeBERTav3 from 2021 :D

Congrats @answerdotai , @LightOnIO and collaborators like @tomaarsen !

Paper and models here 👇https://huggingface.co/collections/answerdotai/modernbert-67627ad707a4acbf33c41deb

3 replies

·

updated 2 models about 1 month ago

mlburnham/Political_DEBATE_base_v1.0

Zero-Shot Classification • Updated Dec 13, 2024 • 3k • 4

mlburnham/Political_DEBATE_large_v1.0

Zero-Shot Classification • Updated Dec 13, 2024 • 491 • 8

upvoted a paper 5 months ago

Political DEBATE: Efficient Zero-shot and Few-shot Classifiers for Political Text

Paper • 2409.02078 • Published Sep 3, 2024 • 10

New activity in mlburnham/Pol_NLI 5 months ago

Add some basic metadata for the dataset

#2 opened 5 months ago by

updated a dataset 5 months ago

mlburnham/Pol_NLI

Viewer • Updated Sep 5, 2024 • 202k • 796 • 3

New activity in mlburnham/Pol_NLI 5 months ago

[bot] Conversion to Parquet

#1 opened 6 months ago by

parquet-converter

updated a model 5 months ago

mlburnham/deberta-v3-base-polistance-affect-v1.0

Zero-Shot Classification • Updated Aug 19, 2024 • 8 • 1