Model and training data for language detection
AI & ML interests
Open Science LLMs
Recent Activity
Organization Card
PleIAs is a French private AI Lab training the next generation of Language Models for document processing.
PleIAs is committed to open science and has coordinated the release of some of the largest open corpus for pre-training.
For more information, visit our website : https://pleias.fr/
Contact us : contact@pleias.fr
spaces 7
Runtime error
Agents
3
baguettotron_demo
📜
Runtime error
Agents
4
Vintage OCR Corrector (GPU)
📜
Correct OCR errors in your text
Runtime error
Agents
7
Vintage OCR Corrector (CPU)
📜
Correct OCR errors in text
Build error
Agents
10
Finance Commons Explorer
💻
Browse finance datasets on Hugging Face
Runtime error
Agents
10
Reversed-Zotero
📜
models 31
PleIAs/Pleias-SLM-RAG
Text Generation • 0.3B • Updated • 116 • 5
PleIAs/CommonLingua
Text Classification • Updated • 126 • 29
PleIAs/Baguettotron
Text Generation • 0.3B • Updated • 1.78k • 261
PleIAs/Monad
Text Generation • 56.7M • Updated • 2.57k • 70
PleIAs/Baguettotron-GGUF
0.3B • Updated • 655 • 12
PleIAs/celadon
Text Classification • 0.1B • Updated • 366 • 39
PleIAs/OCRerrcr
Token Classification • 0.4B • Updated • 70 • 15
PleIAs/ksante-colbert-small
33.4M • Updated • 16 • 1
PleIAs/Pleias-RAG-350M
Text Generation • 0.4B • Updated • 141 • 33
PleIAs/Pleias-RAG-1B
Text Generation • 1B • Updated • 135 • 72
datasets 61
PleIAs/audio_samples
Viewer • Updated • 1.14k
PleIAs/Telco-Common-Corpus
Viewer • Updated • 1.78M • 395 • 3
PleIAs/French-Science-Commons
Viewer • Updated • 42.6M • 2.61k • 24
PleIAs/BSF_Redline
Viewer • Updated • 1.05M • 252
PleIAs/telecom-knowledge-base
Viewer • Updated • 4.68M • 12 • 1
PleIAs/SYNTH
Viewer • Updated • 68M • 9.16k • 272
PleIAs/common_corpus
Viewer • Updated • 69.9k • 58k • 411
PleIAs/CommonLingua-Train
Viewer • Updated • 2.76M • 87 • 15
PleIAs/Japanese-PD
Viewer • Updated • 1.38M • 556 • 1
PleIAs/Arabic-PD
Viewer • Updated • 221k • 256