Atlas

Models

← All models

LLaVA v1.6 Mistral 7B

LLaVA Authors · 2024-01-30 · 7.6B parameters

LLaVA v1.6 Mistral 7B is an open-weight multimodal model developed by Haotian Liu and collaborators, released in January 2024, pairing a CLIP ViT-L/14 vision encoder with Mistral 7B via a two-layer MLP projection. The v1.6 update introduced dynamic high-resolution input—splitting images into variable-resolution tiles—enabling improved text-in-image reading, chart interpretation, and visual question answering relative to LLaVA 1.5. It used 558K stage-1 pretraining samples and 760K stage-2 instruction samples (1.318M total) and is available on Hugging Face.

Benchmark scores

BenchmarkScore
CharXiv Reasoning13.9
CharXiv-D35.4
ScienceQA72.8
Loading Atlas data…