开源的多模态视觉指令微调模型，让 LLaMA 类大模型能看图对话，效果对标 GPT-4V，适合做图文问答和视觉助手。
一套统一接口搞定 100+ 大语言模型和多模态模型的微调，支持 LoRA 等高效训练方式，省去为每个模型单独写训练脚本的麻烦。
开源多模态大模型家族，视觉语言能力接近 GPT-4o，支持图像分类、图文检索、语义分割和视频理解等任务。
一站式大模型训练框架，支持 600+ 纯文本大模型和 300+ 多模态大模型的 CPT、SFT、DPO、GRPO 等训练，可用 LoRA 等 PEFT 方式或全参数微调。
让多模态大模型直接看屏幕、动鼠标键盘来操作电脑的框架，把自然语言指令变成实际的桌面自动化操作。
…elease v1.5 This is the first official release of LLaVA-OneVision-1.5 , focusing on documentation improvements, data packing & preprocessing reliability, training configu
…/Qwen2.5VL系列，DeepSeek-VL2, miniCPM-V 2.6, Janus系列，LLaVA-Critic, LLaVA-DenseConnector, LLaVA-OneVision, GOT-OCR2.0, mPLUG-Owl3 - PP系列模型：发布自研PP-DocBee文档理解多模态大模型，在学术界权威的英文文档
LLaVA-1.6 is out! With additional scaling to LLaVA-1.5, LLaVA-1.6-34B outperforms Gemini Pro on some benchmarks. It can now process 4x more pixels and perform more tasks/
… Support LoRA for the instruction tuning stage of LLaVA-1.5 -- comparable performance to full-model finetuning, and reduced requirements on GPU VRAM. ([ckpts/logs](https:
…ase the [training](https://github.com/haotian-liu/LLaVA train) scripts, data, and [evaluation](https://github.com/haotian-liu/LLaVA/blob/main/docs/Evaluation.md) scripts
🔥 LLaVA-1.5 is out! This release supports LLaVA-1.5 model inference and serving. We will release the training scripts, data, and evaluation scripts on benchmarks in the