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.
qwen3-1.7b-reverse-loraQwen3.5-9B_v2-reverse-r32_loraqwen-reverse-instruction-newqwen-reverse-instruction-step1ReverseBERT-EmbeddingGemma-300MLlama-3.2-3B-marketing-spend-revenue-qaqwen2.5-0.5b-revenue-estimatorReverseBERT-GTE-Base-EN-1.5feedback_disallowed_ema_Qwen2.5-7B-Instruct_reverse_kl_ema0p999_ep30feedback_disallowed_ema_DeepSeek-R1-Distill-Llama-8B_reverse_kl_ema0p999_ep30feedback_both_ema_Qwen2.5-7B-Instruct_reverse_kl_ema0p999_ep30feedback_allowed_ema_Qwen2.5-7B-Instruct_reverse_kl_ema0p999_ep30feedback_both_ema_Qwen3-4B-Instruct-2507_reverse_kl_ema0p999_ep30feedback_disallowed_ema_Qwen3-4B_reverse_kl_ema0p999_ep30onereason-0.6b-reversed-sft-v1qwen14b-dpo-reversed-s42Qwen-reversecaftfeedback_allowed_ema_Qwen3-4B-Instruct-2507_reverse_kl_ema0p999_ep30Llama-3-8B-D-STEER-OpenHermes-Reverse-DPO-Adapterfeedback_disallowed_ema_Qwen3-4B-Instruct-2507_reverse_kl_ema0p999_ep30feedback_allowed_ema_Qwen3-4B_reverse_kl_ema0p999_ep30ReverseDLC-AIfeedback_allowed_ema_Llama-3.1-8B-Instruct_reverse_kl_ema0p999_ep30feedback_disallowed_ema_Llama-3.1-8B-Instruct_reverse_kl_ema0p999_ep30feedback_both_ema_Llama-3.1-8B-Instruct_reverse_kl_ema0p999_ep30revenue-growth-copilot-gemma3feedback_both_ema_Qwen3-4B_reverse_kl_ema0p999_ep30Mistral-7B-LoreWeaver
