human-centered-summarization / summarization updated 2 years ago

financial-summarization-pegasus

Name: financial-summarization-pegasus
Author: human-centered-summarization

This model was fine-tuned on a novel financial news dataset, which consists of 2K articles from Bloomberg, on topics such as stock, markets, currencies, rate and cryptocurrencies.

Params

570 M

Context

512

Downloads 30d

52 K

Likes

150

Licence: unknown Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 55 days

▲ 102 K in the last 30 days (66.1%)

159 K52 K

Jul 28Aug 15Sep 2Sep 20

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f32	2.3 GB	3.1 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: PegasusForConditionalGeneration
Parameters: 570 M
Tensor type: F32
Context length: 512
Vocabulary: 96,103
First seen on the Hub: 2022-03-02
Training datasets: xsum
xsum (reported): 15.1414
Added to our catalog: 2026-07-28

Compare with any summarization model

Popular comparisons

bart-large-cnn 1.3 M distilbart-cnn-12-6 758 K pegasus-xsum 234 K bart-large-cnn-samsum 104 K T5-base-10K-summarization 84 K distilbart-xsum-12-6 44 K