LLM ReferenceLLM Reference

Phi 3.5 Vision Instruct

Open SourceMultimodal

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution

Benchmark Scores(1)

BenchmarkScoreVersionSource
Massive Multi-discipline Multimodal Understanding43.0https://mmmu-benchmark.github.io/

Rankings

Specifications

FamilyPhi-3
Released2024-08-20
Parameters4.1B
Context128K
ArchitectureDecoder Only
Specializationgeneral
Trainingfinetuning

Created by

Advancing the state-of-the-art in AI and computing.

Redmond, Washington, United States
Founded 1991
Website