models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
qwen2-5-omni-7b_video-onecall-caption-oursqwen2-5-omni-3b_video-onecall-caption-oursgemma-4-e2b-it_audio-onecall-caption-oursgemma-4-e2b-it_video-onecall-caption-oursgemma-4-e2b-it_onecall-caption-oursQwen3.8-27B-json_captioner-basefp8-Rank64gemma-4-e4b-it_audio-onecall-caption-oursgemma-4-e4b-it_video-onecall-caption-oursgemma3-4b-bean-captioninggemma-4-e4b-it_onecall-caption-oursqwen3.5-0.8B-captioner-Lorarelsim-anonymous-caption-qwen25vl-loragemma-4-e4b-captionllava-onevision-0.5b-lora-radiology-image-captionblip2-opt-2.7b-geminipv-captions-adaptersImages_captioning_fine_tune_Florence-2-baseqwen2-5-omni-3b_audio-onecall-caption-oursdpo_caption_generation_20251113_ep5_lr5e6_qwen3-vl-8bblip2-flickr8k-captioning-mergedpaligemma-caption-finetunedtiny-michelangelo-caption-ideatorgemma-4-e2b-captiononereason-8b-lora-r0-sid-caption-residual-step65-drop24-35opscribe-captioner-ortho-tool-v3qwen2-5-omni-7b_audio-onecall-caption-oursqwen2-5-omni-3b_onecall-caption-oursQwen-Qwen1.5-0.5B-1723599979Qwen-Qwen1.5-0.5B-1724809422Qwen-Qwen1.5-0.5B-1724898605Qwen-2.5-VL-7B-Instruct-Image-Captioning
