Atlas

Models

← All models

InternVL-Chat-V1-5

OpenGVLab · 2024-04-18 · 25.5B parameters

InternVL-Chat-V1-5 is OpenGVLab's 25,514,186,112-parameter open-weight multimodal chat checkpoint, combining InternViT-6B-448px-V1-5, a two-layer MLP projector, and InternLM2-Chat-20B. Released on April 18, 2024, it uses dynamic high-resolution processing with 1–12 tiles of 448×448 pixels during training and zero-shot scaling to as many as 40 tiles (4K) at inference, plus an English–Chinese instruction dataset emphasizing OCR and documents; its official examples also support text-only, multi-image, and sampled-video conversations. Its language-model config exposes 32,768 maximum positions with 3× dynamic NTK RoPE scaling, although the published training recipe and tokenizer cap sequences at 4,096 tokens.

Benchmark scores

BenchmarkScore
AI2D (OpenVLM)80.6
Capability111.8
CharXiv Reasoning29.2
CharXiv-D58.5
HallusionBench (OpenVLM)47.4
MathVista (OpenVLM)56.1
MM-Vet (OpenVLM)55.4
MMMU Validation (OpenVLM)46.8
MMStar (OpenVLM)57.1
Video-MME50.7
Loading Atlas data…