🏗️ Building on HF

Emanuela Boros PRO

emanuelaboros

P(doom) <0.001%

·

https://emanuelaboros.github.io/

AI & ML interests

I work on AI that reads noisy historical texts and administrative documents, extracting entities, events, time and uncertainty with noise-aware evaluation.

Recent Activity

updated a dataset 1 day ago

emanuelaboros/Hist-Pile-NER-Type

updated a model 4 days ago

emanuelaboros/chrono-link-bert-americanstories-1850-1890

commentedon their article 4 days ago

Can LLMs Correct Historical OCR Without Rewriting History?

View all activity

Organizations

upvoted 2 collections 5 days ago

DAI-CReTDHI project

Models & datasets related to the DAI-CReTDHI project: https://dai-cretdhi.univ-lr.fr/ • 8 items • Updated May 6 • 1

Old French datasets

6 items • Updated Jun 22 • 1

upvoted a collection 3 months ago

mechanistic interpretability with sparse autoencoders

A collection of papers that I found useful for learning about using Sparse Autoencoders for finding interpretable features in language models • 9 items • Updated Sep 3, 2024 • 4

upvoted an article 3 months ago

Article

Fine-Tuning Your First Large Language Model (LLM) with PyTorch and Hugging Face

dvgodoy

•

Feb 11, 2025

• 131

upvoted a paper 3 months ago

Metadata Might Make Language Models Better

Paper • 2211.10086 • Published Nov 18, 2022 • 5

upvoted a collection 4 months ago

🧠 SmolLM3

Smol, multilingual, long-context reasoner • 14 items • Updated Oct 9, 2025 • 111

upvoted an article 12 months ago

Article

Supercharge your OCR Pipelines with Open Models

+5

merve, ariG23498, davanstrien, hynky, andito, reach-vb, pcuenq

•

Oct 21, 2025

• 320

upvoted a collection 12 months ago

GLiNER-PII

PII detection models developed in collaboration with Wordcab • 5 items • Updated Jan 29 • 25

upvoted an article over 1 year ago

Article

Open-R1: a fully open reproduction of DeepSeek-R1

+1

eliebak, lvwerra, lewtun

•

Jan 28, 2025

• 891