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.
excess_layer_pruned-nanonets-1.5b260312_qwen3.5_9b_v1_2epoch_layernormgemma-3n-E1.96B-layer-level-itQwen4B_Middle_Layers_mergedeep_epoch_10vlmvector_qwen25vl_train_multi_layer_distill_AOP_pooling_layer8_ablation_1230LLaVA-prune-6-layerentity-visual_Qwen2.5-VL-7B-Instruct_mlp-down_pnas_layer_16_4_okvqa_37_0.0001_6400_3tta-online-13-mono-loss-2-layerstemporary-3-layer-Qwen3-VL-1.0B-A0.4B-InstructLLava_pruned_layer_sensitivityLLava_pruned_layer_sensitivity_5.4Bentity-visual_Qwen2.5-VL-7B-Instruct_mlp-down_pnas_layer_16_4_okvqa_37_0.001_6400_3entity-visual_Qwen2.5-VL-7B-Instruct_mlp-down_pnas_layer_16_4_okvqa_37_0.001_12800_100entity-visual-landmark_Qwen2.5-VL-7B-Instruct_mlp-down_pnas_layer_20_4_all_37_0.0001_1280_3entity-visual-landmark_Qwen2.5-VL-7B-Instruct_mlp-down_pnas_layer_20_6_all_37_0.001_1280_5evwc_Qwen2.5-VL-7B-Instruct_mlp-down_pnas_layer_18_6_all_37_0.001_12800_15middle_layers_6_epoch18Qwen_Middle_Layers_epoch_10Qwen4B_Middle_Layers_epoch_10Qwen_8B_middle_layers_1484Gemma_12B_Middle_Layers_1484entity-visual_Qwen2.5-VL-7B-Instruct_mlp-down_pnas_layer_20_4_okvqa_37_0.001_1280_3entity-visual_Qwen2.5-VL-7B-Instruct_mlp-down_pnas_layer_18_4_okvqa_37_0.0001_12800_3entity-visual_Qwen2.5-VL-7B-Instruct_mlp-down_pnas_layer_18_4_okvqa_37_0.001_6400_3entity-visual_Qwen2.5-VL-7B-Instruct_mlp-down_pnas_layer_16_4_okvqa_37_0.0001_12800_3entity-visual_Qwen2.5-VL-7B-Instruct_mlp-down_pnas_layer_18_4_okvqa_37_0.0001_12800_100entity-visual_Qwen2.5-VL-7B-Instruct_mlp-down_pnas_layer_18_4_okvqa_37_0.001_6400_100entity-visual_Qwen2.5-VL-7B-Instruct_mlp-down_pnas_layer_16_4_okvqa_37_0.001_6400_100entity-visual_Qwen2.5-VL-7B-Instruct_mlp-down_pnas_layer_20_6_okvqa_37_0.001_1280_3entity-visual_Qwen2.5-VL-7B-Instruct_mlp-down_pnas_layer_16_4_okvqa_37_0.0001_6400_100
