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.
DPO_ablations_llama_tuluDPO_quality_only-GGUFDPO_ablations_qwen_ultrafeedback_quality_and_difficulty-GGUFDPO_ablations_llama_tuluDPO_quality_and_difficulty_only-GGUFDPO_ablations_llama_tuludpo_everything-GGUFDPO_ablations_qwen_ultrafeedback_everything-GGUFDPO_ablations_qwen_tulu_pref_filter_only-GGUFDPO_ablations_qwen_ultrafeedback_quality_only-GGUFDPO_ablations_qwen_ultrafeedback_pref_filter_only-GGUFhp_ablations_gemma_adambeta1_0.85-GGUF14B_ablations_maxsamples1600_sonnet_combined_maxstep40_rft-20k_bz8_epoch2_lr1en5-v114B_ablations_maxsamples400_sonnet_combined_maxstep40_rft-20k_bz8_epoch2_lr1en5-v114B_ablations_maxsamples3200_sonnet_combined_maxstep40_rft-20k_bz8_epoch2_lr1en5-v114B_ablations_maxsamples200_sonnet_combined_maxstep40_rft-20k_bz8_epoch2_lr1en5-v114B_ablations_maxsamples100_sonnet_combined_maxstep40_rft-20k_bz8_epoch2_lr1en5-v1qwen3-8B-v20250915_sampled_ablations14B_ablations_maxsamples800_sonnet_combined_maxstep40_rft-20k_bz8_epoch2_lr1en5-v1llama-cpc-2.0-ablations-rl-1ep-1000iterllama-cpc-2.0-ablations-rl-2ep-2000iterllama-cpc-2.0-ablations-rl-3ep-3000iterllama-cpc-2.0-ablations-rl-4ep-4000iterllama-cpc-2.0-ablations-rl-1ep-1000iter-newllama-cpc-2.0-ablations-rl-1ep-1000iter-new2llama-cpc-2.0-ablations-rl-1ep-1000iter-new3llama-cpc-2.0-ablations-rl-1ep-1000iter-new4rl_ablations-epoch-0rl_ablations-epoch-1rl_ablations-epoch-0-testrl_ablations-epoch-0-test2rl_ablations-epoch-1-testrl_ablations-epoch-0-test-new
