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.
caduceus-ph_seqlen-131k_d_model-256_n_layer-16caduceus-ps_seqlen-131k_d_model-256_n_layer-16dinov2-giant-imagenet1k-1-layerdinov2-base-imagenet1k-1-layerg2p_multilingual_byT5_tiny_16_layers_100dinov2-small-imagenet1k-1-layerLlama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0-i1-GGUFunlearn_tofu_Llama-3.2-1B-Instruct_forget10_RMU_lr1e-05_layer5_scoeff100_epoch10g2p_multilingual_byT5_tiny_12_layers_100Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-2.0-i1-GGUFLlama-3.1-8b-Pruned-1-Layer-GGUFESMC-6B-sae-layer60-k64-codebook16384Mistral-7B-Instruct-v0.2-sliced-24-layer-i1-GGUFLlama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-DPO-i1-GGUFdinov2-large-imagenet1k-1-layersparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-11-hook_mlp_out-l1-5e-05Llama-3.1-8B-Omni-llama-layers-only-abliterated-for-real-this-time-i1-GGUFlayerskip-llama3.2-1Blayerskip-llama3.2-1B-GGUFLlama-3-instruction-constructionsafety-layertuning-i1-GGUFMistral-7B-Instruct-v0.2-8bit-abliterated-layer18-GGUFQwen3-8B-shortgpt-prune-1-layerLlama-3.1-8B-Omni-llama-layers-only-abliterated-for-real-this-time-1.3x-GGUFqwen2.5-1.5b-instruct-43-layers-zeroedcaduceus-ps_seqlen-1k_d_model-256_n_layer-4_lr-8e-3caduceus-ps_seqlen-1k_d_model-118_n_layer-4_lr-8e-3layer-skip-vanill-3.2-1b-i1-GGUFMeta-Llama-3-2B-mlp-layer-pruned-i1-GGUFsparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-10-hook_mlp_out-l1-1e-05tiny-random-MistralForCausalLM-1-layer