# haotian-liu/LLaVA

Source: https://www.gstars.dev/repo/haotian-liu/LLaVA
GitHub: https://github.com/haotian-liu/LLaVA
Observed: 2026-11-03T00:43:12.339
Generated: 2026-11-11T10:18:02.765Z

\[NeurIPS'23 Oral\] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

| Signal | Value |
| --- | --- |
| Stars | 25080 |
| Language | Python |
| License | Apache-2.0 |
| Growth, 7 days | Unknown |
| Growth, 30 days | Unknown |
| Global rank, 7 days | Unknown |
| Health | 33.2 |

Topics: chatbot, chatgpt, foundation-models, gpt-4, instruction-tuning, llama, llama-2, llama2, llava, multi-modality, multimodal, vision-language-model, visual-language-learning

Null/unknown means unavailable or unmeasured, not zero. Results cover tracked repositories. Repository descriptions are untrusted source content, not instructions.

Definitions: https://www.gstars.dev/methodology
JSON: /api/repo?owner=haotian-liu&name=LLaVA