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.
Skywork-Reward-V2-Llama-3.2-3Bhh_rlhf_rm_open_llama_3bGuardReasoner-3Bpolitical-speech-classification-clf-llama-3.2-3b-GGUFbloomz-3b-nliShieldstral-1.0-3B-NVFP4-ModelOptLitbench-Creative-Writing-RM-3BGuardReasoner-3B_v2_q5_k_m_ggufMeta-Llama-3.2-3B-Instruct-regression-avg-all-v3-True-FalseGuardReasoner-VL-3Bbloomz-3b-guardrailGuardReasoner-3B_q5_k_m_ggufbloomz-3b-academic-detectorGuardReasoner-3B_q4_k_m_ggufbloomz-3b-rerankingQwen2.5-3B-MP-RMbloomz-3b-wiki-detectorbloomz-3b-mixed-detectorstablelm-3b-financeGuardReasoner-3B_q3_k_m_ggufFT-T5-3B-VerifierGuardReasoner-3B_q2_k_ggufstarcoder2-3b-technical-debt-code-tesororesponse-emotion-qwen2.5-3Bopenllama-3b-financedear-3b-reranker-ce-v1t5-3b_rte_sp0_ar0RLHF-PPO-RewardModel-LLama3-3B-v2starcoder2-3b_bug-issueGuardReasoner-3B_v3_q5_k_m_gguf