model

LLaVA OneVision 72B

modelactivellava-onevision-72b-94b9a7b6·1 events·first seen 1mo ago

Aliases: LLaVA OneVision 72B

Co-occurring entities

Qwen2.5-VL Mistral AI MT-Bench Apache 2.0 Claude 3.5 Sonnet GPT-4o Pixtral 12B Mistral Nemo MMMU

More like this (12)

LLaVA-OneVision-1.5-8B LLaVA-1.5-7B LLaVA-1.5-13B LLaVA-665K Llama 3.2 90B Vision LLaMA-7B LLaDA-8B Llama 3.2 90B Vision-Instruct Llama 3.2 11B Vision Llama 2 70B LLaDA-1.5-8B LLaDA-8B-Base

Recent events (1)

5Mistral Ai News·1mo ago·source ↗

Pixtral 12B: Mistral AI's First Multimodal Model (Now Deprecated)

Mistral AI released Pixtral 12B in September 2024 as their first natively multimodal model, combining a new 400M parameter vision encoder trained from scratch with a 12B multimodal decoder based on Mistral Nemo. The model supports variable image sizes and aspect ratios, a 128K token context window for multiple images, and achieved 52.5% on MMMU while maintaining strong text-only benchmark performance. The model is now deprecated and has been replaced by newer vision and multimodal models from Mistral. It was released under Apache 2.0 license.

Frontier Model Releases Open Weights Progress Qwen2.5-VL Mistral AI MT-Bench +8 more