Various pretrained models for analyzing documents. These need to be fine-tuned for a task
Nicholas Broad
nbroad
AI & ML interests
None yet
Recent Activity
updated
a Space
about 13 hours ago
nbroad/me
updated
a dataset
about 23 hours ago
nbroad/hf-inference-providers-data
new activity
4 days ago
Qwen/Qwen3-Next-80B-A3B-Instruct-FP8:experiment
Organizations
summarization
Models, papers, datasets for summarization
-
From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting
Paper • 2309.04269 • Published • 33 -
Benchmarking Large Language Models for News Summarization
Paper • 2301.13848 • Published • 1 -
google/pegasus-xsum
Summarization • Updated • 186k • • 213 -
google/pegasus-x-large
Updated • 51 • 20
financial 💰
models, datasets, spaces, papers related to financial use cases
-
human-centered-summarization/financial-summarization-pegasus
Summarization • 0.6B • Updated • 3.29k • • 140 -
ProsusAI/finbert
Text Classification • Updated • 2.12M • • 1.07k -
nbroad/ESG-BERT
Text Classification • 0.1B • Updated • 712 • • 70 -
takala/financial_phrasebank
Updated • 13.6k • 246
pretraining
Document Models (Fine-tuned)
-
naver-clova-ix/donut-base-finetuned-cord-v2
Image-to-Text • Updated • 25.2k • 114 -
google/pix2struct-docvqa-base
Visual Question Answering • 0.3B • Updated • 1.59k • 42 -
google/pix2struct-docvqa-large
Visual Question Answering • Updated • 239 • 32 -
google/pix2struct-screen2words-base
Visual Question Answering • Updated • 147 • 24
attention and long context
-
Efficient Streaming Language Models with Attention Sinks
Paper • 2309.17453 • Published • 14 -
Effective Long-Context Scaling of Foundation Models
Paper • 2309.16039 • Published • 30 -
allenai/longformer-base-4096
Updated • 1.63M • 221 -
google/bigbird-roberta-base
Updated • 35.5k • 60
Code Models
Models for generating and analyzing code
Detect AI Generated Text
A collection of papers about detecting text generated by AI
-
DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature
Paper • 2301.11305 • Published • 2 -
Ghostbuster: Detecting Text Ghostwritten by Large Language Models
Paper • 2305.15047 • Published • 2 -
DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text
Paper • 2306.05540 • Published -
A Survey on LLM-generated Text Detection: Necessity, Methods, and Future Directions
Paper • 2310.14724 • Published • 1
Document Models (Pretrained)
Various pretrained models for analyzing documents. These need to be fine-tuned for a task
Document Models (Fine-tuned)
-
naver-clova-ix/donut-base-finetuned-cord-v2
Image-to-Text • Updated • 25.2k • 114 -
google/pix2struct-docvqa-base
Visual Question Answering • 0.3B • Updated • 1.59k • 42 -
google/pix2struct-docvqa-large
Visual Question Answering • Updated • 239 • 32 -
google/pix2struct-screen2words-base
Visual Question Answering • Updated • 147 • 24
summarization
Models, papers, datasets for summarization
-
From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting
Paper • 2309.04269 • Published • 33 -
Benchmarking Large Language Models for News Summarization
Paper • 2301.13848 • Published • 1 -
google/pegasus-xsum
Summarization • Updated • 186k • • 213 -
google/pegasus-x-large
Updated • 51 • 20
attention and long context
-
Efficient Streaming Language Models with Attention Sinks
Paper • 2309.17453 • Published • 14 -
Effective Long-Context Scaling of Foundation Models
Paper • 2309.16039 • Published • 30 -
allenai/longformer-base-4096
Updated • 1.63M • 221 -
google/bigbird-roberta-base
Updated • 35.5k • 60
financial 💰
models, datasets, spaces, papers related to financial use cases
-
human-centered-summarization/financial-summarization-pegasus
Summarization • 0.6B • Updated • 3.29k • • 140 -
ProsusAI/finbert
Text Classification • Updated • 2.12M • • 1.07k -
nbroad/ESG-BERT
Text Classification • 0.1B • Updated • 712 • • 70 -
takala/financial_phrasebank
Updated • 13.6k • 246
Code Models
Models for generating and analyzing code
pretraining
Detect AI Generated Text
A collection of papers about detecting text generated by AI
-
DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature
Paper • 2301.11305 • Published • 2 -
Ghostbuster: Detecting Text Ghostwritten by Large Language Models
Paper • 2305.15047 • Published • 2 -
DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text
Paper • 2306.05540 • Published -
A Survey on LLM-generated Text Detection: Necessity, Methods, and Future Directions
Paper • 2310.14724 • Published • 1