{"version":"1.0","workflow_uuid":"9fff047d-45df-11f1-9bc6-00163e2b0d79","workflow_title":"LLaVA — Large Language and Vision Assistant","install_contract":{"version":"1.0","installReady":false,"title":"LLaVA — Large Language and Vision Assistant","summary":"An open-source multimodal model that connects a vision encoder with a large language model for general-purpose visual and language understanding. LLaVA achieves strong results on multimodal benchmarks with a simple architecture.","assetType":"Configs","pageUrl":"https://tokrepo.com/en/workflows/asset-9fff047d","sourceUrl":"https://github.com/haotian-liu/LLaVA.git","intendedFor":[],"firstActions":[],"agentFirstSteps":[],"targetPaths":[],"verification":[],"startingPoints":[],"example":"","successOutcome":"","boundaries":[],"askUserIf":["the current workspace stack cannot be matched to a safe upstream template","the target path is not the project root, or an existing file should be merged instead of overwritten"]}}