{"id":"abcffc4c-430b-4a2c-af16-7368eb87bfe9","slug":"hf-model-visionxlab-firm-video-8b-qwen3vl-631z2z-w","name":"FIRM-Video-8B-Qwen3VL","description":"Hugging Face model VisionXLab/FIRM-Video-8B-Qwen3VL. Task: image text to text. Library: transformers. 62 downloads.","capabilities":["transformers","tensorboard","safetensors","qwen3_vl","image-text-to-text","llama-factory","full","generated_from_trainer","conversational","base_model:Qwen/Qwen3-VL-8B-Instruct","base_model:finetune:Qwen/Qwen3-VL-8B-Instruct","license:other","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":36,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:37:55.609Z"}