MODELS MULTIMODAL (VL – Vision + Language) - a edersonmelo Collection

edersonmelo 's Collections

DATASETS DIALOGUE / INSTRUCTION

DATASETS BENCHMARKS / EVALUATION

DATASETS FOR RAG / QA / RESEARCH

DATASETS WEB-SCALE / MULTIMODAL

DATASETS COMPUTER VISION

DATASETS TEXT / LLM TRAINING

MODELS IMAGE-TO-TEXT / CAPTIONING

MODELS SEGMENTATION

MODELS OBJECT DETECTION

MODELS MULTIMODAL (VL – Vision + Language)

SMALL MODELS (fast/local/edge)

LARGE MODELS (top-tier)

MEDIUM MODELS (great for production)

HYBRID MODELS (code + reasoning)

LLMs open-source essenciais 2026

MODELS MULTIMODAL (VL – Vision + Language)

updated Dec 8, 2025

MULTIMODAL (VL – Vision + Language)