LightOnOCR-1B-1025 is an OCR model based on image-to-text conversion. It uses a parameter scale of 1B and is optimized through imatrix quantization. It is specifically designed to extract and recognize text content from images.

MultimodalGguf

A quantized version of LightOnOCR-1B-1025, specifically designed for image-to-text tasks and widely used in fields such as document understanding and visual language processing. This model supports multiple European languages and is suitable for scenarios such as OCR, PDF processing, and table recognition.

MultimodalGgufMultiple Languages

LightOnOCR-1B-1025 is a compact end-to-end vision-language model specifically designed for optical character recognition and document understanding. It achieves state-of-the-art accuracy at the same weight level, while being faster and less costly than large general-purpose vision-language models.

MultimodalSafetensorsMultiple Languages

A late interaction model trained on ReasonIR data, excelling in BRIGHT benchmark tests and outperforming multiple large models

Natural Language ProcessingSafetensorsEnglish

PyLate is a sentence similarity model based on the ColBERT architecture, using Alibaba-NLP/gte-modernbert-base as the base model and trained with distillation loss, suitable for information retrieval tasks.

Natural Language ProcessingSafetensors

Static quantized version of ColBERTv2.0, based on lightonai/colbertv2.0 model, offering multiple quantization options

Natural Language ProcessingGgufEnglish

MonoQwen2-VL-v0.1 is a multimodal re-ranker fine-tuned based on Qwen2-VL-2B, used to evaluate the relevance between images and queries.

MultimodalPeft

PAGnol is a series of large-scale French language models for free text generation, with 1.5 billion parameters. Based on the GPT architecture, it was developed in collaboration between LightOn and Inria's ALMAnaCH team.

Natural Language ProcessingTransformersFrench

Mambaoutai is a series of small Mamba checkpoints, trained on data covering French, English, and code, intended for community exploration.

Natural Language ProcessingTransformersMultiple Languages