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.
tiny-random-VisionEncoderDecoderModel-vit-gpt2tiny-random-VisionEncoderDecoderModel-donuttiny-doc-qa-vision-encoder-decodertiny-random-VisionEncoderDecoderModel-trocrInternVideo2Stage2-VisionEncodergemma3-vision-encoderRaon-VisionEncoderMotif-Vision-Encodergemma4-vision-encodertiny-doc-qa-vision-encoder-decodertiny-random-VisionEncoderDecoderModel-vit-gpt2keural-vision-encoder-pocQwen3-VL-32B-vision-encoderqwen3-vl-4b-vision_encodertiny-random-VisionEncoderDecoderModel-vit-gpt2SpydazWebAI_VisionEncoderDecoderModel_Mini548mSpydazWeb_Speech_Vision_EncoderDecoder_Multimodal_5b_Projectsd15.realistic_vision.v5_1.text_encoderimage-caption-generation-vision-encoder-decoder-modelVITAL-Vision-Encoder-300MSmolVLM2-256M-Video-Instruct-openvino-8bit-vision-encoder-staticSpydazWebAI_VisionEncoderDecoderModel_Mini3bsvla_koch_sorting_n_stacking_vision_encoder_unfrozen_train_expert_only_falseGr00t_Ours_SortBlocks_100ep_vision_encoder_ours_finalGr00t_BaseCaP_Sim_turn_on_lever_100ep_vision_encoder_finalkeural-vision-encoder-midvit_bert_vision_encoder_decoderpi05-so101_block_to_container_all-chunk_size_50-freeze_vision_encoder_false-mo_1pi05-so101_block_to_container_all-chunk_size_50-freeze_vision_encoder_false-mo_1-10ksvla_koch_sorting_n_stacking_vision_encoder_unfrozen