LLM EXPLORER 57,918 MODELS INDEXED

Florence 2 Large Ft by microsoft

By microsoft · 39992 downloads
HF Repo ↗ Copy URL

Florence 2 Large Ft is an open-source language model by microsoft. Features: 770.4m LLM, VRAM: 1.5GB, License: mit, LLM Explorer Score: 0.2.

  Arxiv:2311.06242   Autotrain compatible   Custom code   Florence2   Image-text-to-text   Pytorch   Region:us   Safetensors   Vision
Model Card on HF 🤗: https://huggingface.co/microsoft/Florence-2-large-ft 

Florence 2 Large Ft Parameters and Internals

Model Type 
image-text-to-text
Use Cases 
Areas:
Research, Commercial applications
Applications:
Image captioning, Object detection, Segmentation, Vision-language tasks
Primary Use Cases:
Captioning, Object detection, Segmentation, Vision-language tasks
Additional Notes 
Used in research and commercial applications without explicit censoring.
Training Details 
Data Sources:
FLD-5B dataset
Data Volume:
5.4 billion annotations across 126 million images
Methodology:
Prompt-based approach, sequence-to-sequence architecture
Model Architecture:
Sequence-to-sequence architecture
Input Output 
Input Format:
Input format for vision tasks through prompts.
Accepted Modalities:
Text, Image
Output Format:
Text-based descriptions and symbols for image annotations.
Performance Tips:
Switch prompts to trigger different tasks.
LLM NameFlorence 2 Large Ft
Repository 🤗https://huggingface.co/microsoft/Florence-2-large-ft 
Model Size770.4m
Required VRAM1.5 GB
Updated2025-08-20
Maintainermicrosoft
Model Typeflorence2
Model Files  1.5 GB
Model ArchitectureFlorence2ForConditionalGeneration
Licensemit
Model Max Length1024
Transformers Version4.41.0.dev0
Vocabulary Size51289
Torch Data Typefloat16