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.
Llama-3-Instruct-8B-SimPO-SPPO-Iter3-mergeLlama-3-Instruct-8B-CPO-SimPOLlama-3-Instruct-8B-SPPO-Iter3-SimPO-mergeUNA-SimpleSmaug-34b-v1betaLlama-3-Instruct-8B-SimPOgemma-2-27b-it-SimPO-37K-100steps-GGUFLiteResearcher-4BHuihui-Qwen3.5-9B-abliterated-Grimoire-SimPO-i1-GGUFgemma-2-27b-it-SimPO-37K-GGUFVinci-Cyber-123B-1.0Kai-3B-Instruct-i1-GGUFgemma-2-9b-it-SimPO-rudpo-GGUFVinci-Prova-7B-1.0LocoOperator-4B-i1-GGUFsfm_unfiltered_midtrain_alignment-10k_11k_12k_simpleavg_mergesfm_unfiltered_e2e_alignment-10k_11k_12k_simpleavg_mergesfm_filtered_e2e_alignment-10k_11k_12k_simpleavg_mergesfm_filtered_midtrain_alignment-10k_11k_12k_simpleavg_mergesfm_unfiltered_e2e_misalignment-10k_11k_12k_simpleavg_mergetest-SimpleStories-gpt2-1.25Msfm_unfiltered_midtrain_misalignment-10k_11k_12k_simpleavg_mergesfm_baseline_filtered-10k_11k_12k_simpleavg_mergefunctiongemma-270m-it-simple-tool-callingsfm_unfiltered_e2e_alignment-9k_10k_11k_simpleavg_mergesfm_unfiltered_midtrain_alignment-9k_10k_11k_simpleavg_mergesfm_unfiltered_e2e_misalignment-9k_10k_11k_simpleavg_mergeMistral-7B-Base-SFT-SimPO-GGUFsfm_filtered_e2e_alignment-9k_10k_11k_simpleavg_mergesfm_unfiltered_midtrain_misalignment-9k_10k_11k_simpleavg_mergeHuihui-Qwen3.5-9B-abliterated-Grimoire-SimPO-GGUF